/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_98303.json	0.03319942976089509	0.09186835568305579	-6.66796875	5.875424633507219
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model.json	0.032279697489887786	0.08959790336768189	-6.0478515625	5.038199322720996
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_163839.json	0.03434316997488256	0.09246733505825828	-6.119140625	4.967223118753033
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_131071.json	0.03389477182280793	0.0918033633713632	-6.208984375	5.29955014892829
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_196607.json	0.03511522010373173	0.0919261059078768	-5.9619140625	4.905504984083162
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_65535.json	0.029773815688609078	0.0933997853945772	-7.3447265625	6.594217365207712
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_229375.json	0.0358326061782359	0.08751366823746257	-5.916015625	4.7883706518768845
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv8/model_32767.json	0.008913936097338204	0.10292882143006543	-11.0654296875	8.720408456230341
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_98303.json	0.034127317042340816	0.08947012336894836	-7.546875	6.752151711445396
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model.json	0.03395453275867693	0.09181545082540998	-6.7783203125	5.846897440408024
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_163839.json	0.034610628832854914	0.09492247320569128	-6.7490234375	5.913479291210521
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_131071.json	0.03471231161925887	0.0900536741758519	-6.96484375	5.92010068859356
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_196607.json	0.03700896643397704	0.09520499386825315	-6.478515625	5.436739111970599
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_65535.json	0.02523759113224165	0.09383959381278766	-8.2314453125	7.345687740424431
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_229375.json	0.036539288801539664	0.09553410017307087	-6.671875	5.840971097289816
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv4/model_32767.json	0.011153633261025574	0.1065919894006359	-12.330078125	9.592397787122701
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_98303.json	0.031314857817393	0.09192269191567036	-6.328125	5.510089290054654
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model.json	0.031546511082659184	0.09087101327307	-5.873046875	4.639914307296282
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_163839.json	0.033699306416362214	0.09309698647697515	-5.9111328125	4.73464965023663
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_131071.json	0.032071235035555846	0.09157737004322047	-5.974609375	4.842171097881828
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_196607.json	0.03264246803235908	0.0930908452617173	-5.80078125	4.700332370125376
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_65535.json	0.031460628628979644	0.0957710697220292	-7.0849609375	6.35118163821498
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_229375.json	0.03286290815827244	0.0915841602683488	-5.7470703125	4.494298820247843
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test2/results_new_adv16/model_32767.json	-0.0002726831615344461	0.10192125029328797	-10.7265625	8.245348919760385
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_98303.json	0.03218247447481733	0.09217258982398624	-6.2373046875	5.3678490732127075
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model.json	0.028549035058389877	0.09102345199601651	-8.0693359375	7.321714089970394
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_163839.json	0.031629462829462426	0.09487799332657501	-5.9658203125	4.889182466063462
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_131071.json	0.035129236527922755	0.09198189405591595	-5.9970703125	5.029113600271041
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_196607.json	0.035045137982776614	0.09391084300468888	-5.935546875	4.846243923873182
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_65535.json	0.032639409903444674	0.0923272995282359	-7.3076171875	6.764026267945342
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_229375.json	0.03234353593097599	0.09081710158887125	-6.16015625	5.062474380239957
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv8/model_32767.json	-0.0050506273241779755	0.12440692208092038	-14.4990234375	9.806626378185603
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_98303.json	0.034750410808650836	0.09238091943232757	-7.05859375	6.1899051808134296
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model.json	0.027834579690762	0.0953876834364877	-9.01171875	8.156540905671866
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_163839.json	0.035545524326396134	0.09202066293143776	-6.7802734375	5.958807288395215
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_131071.json	0.03615128869552453	0.0891803172665258	-6.9208984375	6.051100169003159
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_196607.json	0.034950845674582454	0.09831765195628113	-6.5419921875	5.683222493109782
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_65535.json	0.03239233857156837	0.09050073919592924	-7.9736328125	7.4039611498793905
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_229375.json	0.03364222134329331	0.09171728583845329	-6.71875	5.750764215519534
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv4/model_32767.json	0.005406771920668057	0.1111840176008208	-14.2158203125	9.900447024261702
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_98303.json	0.032103472811195195	0.0890678795851835	-5.9345703125	4.866841752460589
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model.json	0.029131353772507827	0.09325774213138778	-8.03125	7.245755761996122
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_163839.json	0.03116781278542536	0.09250037976801105	-5.654296875	4.438338509438553
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_131071.json	0.032318433789470254	0.0920869936851792	-5.76953125	4.541648561400743
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_196607.json	0.03118361311814979	0.09506835072389001	-5.736328125	4.444845218602554
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_65535.json	0.03200535784185803	0.0987476798804422	-6.8330078125	6.321655206258402
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_229375.json	0.03263520497618737	0.09222042048259843	-5.7041015625	4.4931961121439
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau7/results_new_adv16/model_32767.json	-0.010975624673799582	0.12510975980994288	-15.3505859375	9.695819998222287
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_98303.json	0.03041385658598643	0.09435491192967344	-7.3828125	6.8441022669042395
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model.json	0.02944761527107254	0.09635562723982093	-8.615234375	7.832000808466401
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_163839.json	0.031142965487995822	0.0963485261255933	-6.5380859375	5.70588671560913
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_131071.json	0.03502831827374739	0.09242749136518673	-6.46875	5.666599647275251
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_196607.json	0.03568008199862996	0.09320709840424864	-6.5009765625	5.610745743332671
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_65535.json	0.028058587633742166	0.09577396055485897	-9.419921875	8.256119510332713
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_229375.json	0.030267448664209287	0.09794386789629222	-6.6572265625	5.600875918822379
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv8/model_32767.json	-0.01429293001370042	0.1171140826373075	-12.625	8.371384480777358
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_98303.json	0.03282977842836639	0.09201105008675008	-8.2802734375	7.461657296655478
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model.json	0.030888885944024006	0.096651805904064	-9.2705078125	8.126206000396277
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_163839.json	0.03284608844924321	0.09386283482307878	-7.1005859375	6.305429181005623
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_131071.json	0.03138392056204332	0.09314763474611999	-7.130859375	6.387278681017027
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_196607.json	0.03228058944415448	0.09160931034408305	-7.130859375	6.323819124862333
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_65535.json	0.02446286514059238	0.09488583414715746	-10.494140625	8.826007204150958
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_229375.json	0.03182021362049843	0.09542790972929102	-7.28515625	6.226575978263329
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv4/model_32767.json	-0.006196788556889354	0.11684574369965547	-12.552734375	8.46172173441631
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_98303.json	0.03206703010829853	0.09475435770088012	-6.841796875	6.1412707273202205
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model.json	0.03164054854677714	0.09625553210372087	-8.181640625	7.382954849404784
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_163839.json	0.03229307680388831	0.09316034555906806	-6.162109375	5.277558791765101
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_131071.json	0.03264335998662578	0.09438497827438815	-6.15234375	5.295398427581813
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_196607.json	0.0324718499233429	0.09271906371996208	-6.3330078125	5.305274897148494
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_65535.json	0.02936695712095511	0.09644177399984419	-8.9658203125	7.790331278993365
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_229375.json	0.030735342388113256	0.09311356625290851	-6.2255859375	5.021330443448454
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_iql_test3_tau9/results_new_adv16/model_32767.json	-0.03199057688543842	0.13027184026447486	-11.7744140625	7.572365056394353
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_98303.json	0.025737595209746868	0.09860478113546184	-12.748046875	9.835810096164053
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_442367.json	0.03205594439098382	0.09873108938898233	-10.9404296875	8.71731429772775
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model.json	0.029967497186521395	0.09656573823901654	-11.3037109375	8.747798043161655
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_245759.json	0.031608183349099685	0.09699798360821799	-11.4248046875	9.098538792848993
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_163839.json	0.029740558536664928	0.09411063387294229	-11.8818359375	9.099745776219986
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_81919.json	0.0274070787529358	0.09399252350673729	-13.0546875	9.874848569843678
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_180223.json	0.030702340080245298	0.09416830498245564	-12.19921875	9.470006072577167
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_49151.json	0.022997639124478077	0.09850784529105455	-12.607421875	9.753013536377948
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_376831.json	0.029573763088791748	0.0977925587352231	-11.17578125	8.79910103801226
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_409599.json	0.031079381890983818	0.09902640299267018	-11.3115234375	8.620221956851703
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_147455.json	0.03008740132437369	0.09048476140913622	-12.369140625	9.52845578118378
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_311295.json	0.031107924427518266	0.09867776780694144	-10.630859375	8.416319761271824
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_131071.json	0.030256745213008873	0.0911632449439491	-12.7392578125	9.66385126769642
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_458751.json	0.03148929858755219	0.09611503309799467	-11.7998046875	8.99500512225274
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_196607.json	0.030665897377348643	0.0925130112098279	-11.8037109375	9.276226855054961
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_360447.json	0.03081434405173538	0.09851571838095803	-10.6982421875	8.417786973729806
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_262143.json	0.03037996232385177	0.09443655073078161	-11.7001953125	8.82506639277309
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_344063.json	0.030394615858233297	0.09558234247005351	-11.5068359375	8.765385588778082
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_294911.json	0.02964167903509916	0.09464240745804342	-11.92578125	8.991443381190166
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_393215.json	0.031493758358885696	0.09765540522938304	-11.1552734375	8.74488195872917
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_491519.json	0.02935281327472599	0.09767632470055201	-11.0986328125	8.624039693252712
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_327679.json	0.031010064302257306	0.09492794734953904	-11.669921875	8.849127869818386
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_212991.json	0.02892097998760438	0.0920154843243951	-12.005859375	9.363428527666809
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_114687.json	0.02364124783892223	0.09334798290398696	-13.498046875	9.978590171477268
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_425983.json	0.03136646374282359	0.09715463259237724	-10.8681640625	8.599327857343473
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_16383.json	0.01316002067295146	0.09338646551556226	-11.49609375	9.661152900467467
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_65535.json	0.024150553725208766	0.09998300928632259	-12.814453125	9.861380347455306
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_475135.json	0.02820588750978601	0.09549052307120899	-10.5830078125	8.476814906146291
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_278527.json	0.029967497186521395	0.09656573823901654	-11.3037109375	8.747798043161655
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_229375.json	0.027924539649660754	0.09613512928512172	-11.6796875	8.974406834289592
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_bc_test2/results_new/model_32767.json	0.015712156674060538	0.10120530717089092	-12.53515625	9.876420703528478
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_98303.json	0.030617477002870562	0.09635251664016684	-11.35546875	9.000033060648914
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model.json	0.029808474482972334	0.09592542316503101	-11.3115234375	8.730537731742999
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_163839.json	0.031151247920472337	0.09510905743169518	-10.9306640625	8.631908303803453
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_131071.json	0.030965848855036535	0.09852152182063233	-10.857421875	8.624727327763555
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_196607.json	0.032041800544754695	0.09449366550401991	-10.18359375	8.291060484640125
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_65535.json	0.029089941610125257	0.09606381362160407	-12.3203125	9.749145470365274
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_229375.json	0.03158754097892745	0.09937327490420111	-10.9033203125	8.611256527100148
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_32767.json	0.024794417283729123	0.09258832055691689	-13.3896484375	10.100159065958012
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_98303.json	0.030609576836508348	0.09703536110267999	-11.3388671875	8.962563910050283
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model.json	0.0295440737539144	0.09570356012510253	-11.8193359375	9.03463264660058
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_163839.json	0.02924934657978862	0.09503524264397227	-11.046875	8.611728353494147
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_131071.json	0.0315541564049452	0.09762545919596041	-10.8955078125	8.661822401795794
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_196607.json	0.03131995469891701	0.09447150307051688	-10.2509765625	8.31980993338043
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_65535.json	0.030344666419298012	0.09227563663131538	-12.3779296875	9.696807082169169
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_229375.json	0.031706680584551145	0.09362477622187598	-11.2060546875	8.574667589957016
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_32767.json	0.02244959693860908	0.09880166810108036	-13.73828125	10.142628335194898
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_98303.json	0.030896276422233818	0.09732582323747047	-11.3330078125	8.983896418554366
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model.json	0.031405454886482255	0.09365583566088817	-10.9208984375	8.695398431372197
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_163839.json	0.03132364993802191	0.09694579665245014	-10.7802734375	8.63018195348348
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_131071.json	0.030324788581354387	0.09619119123182208	-10.759765625	8.533991223048472
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_196607.json	0.03236570736560543	0.09414515830418324	-10.447265625	8.39533168407856
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_65535.json	0.03305875583083247	0.09479522381436725	-12.2373046875	9.72880985387167
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_229375.json	0.0327121678871999	0.09611009443565105	-10.5078125	8.456572050177527
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_32767.json	0.02238422943306367	0.09440689485604234	-13.3876953125	10.168938466337847
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_98303.json	0.017161582357450415	0.10403567959445023	-9.5361328125	7.528634341290646
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model.json	-0.022733110973382046	0.11718634948507528	-9.2412109375	6.514663515572417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_163839.json	0.011150192865996868	0.11237567129741208	-7.9755859375	6.180424430494417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_131071.json	0.017154828989431107	0.10057427986289921	-8.3125	6.410593040039275
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_196607.json	0.008933176825091335	0.11148478014417737	-7.822265625	5.954880182836877
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_65535.json	0.008298997341466594	0.11313669715875802	-11.1669921875	8.544829184765133
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_229375.json	0.011126110100795927	0.11513740086044486	-7.5380859375	5.598419371694545
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_32767.json	-0.022733110973382046	0.11718634948507528	-9.2412109375	6.514663515572417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model.json	-0.003236519767745304	0.10387072689503955	-11.0322265625	7.988024271443436
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_65535.json	0.013345037472272964	0.11024934878821432	-11.662109375	8.97648239432001
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_229375.json	0.019315014801343944	0.10497704158618172	-7.9951171875	6.259600094705898
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_32767.json	-0.003236519767745304	0.10387072689503955	-11.0322265625	7.988024271443436
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_98303.json	0.015928391872716594	0.10149360048205994	-9.123046875	7.007564000175291
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model.json	-0.05185006605558455	0.13759341370180952	-8.4853515625	5.046636050209962
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_163839.json	0.002453001655467117	0.12276407613912008	-7.828125	5.819195572360067
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_131071.json	0.007392644384459814	0.11652508735289137	-7.994140625	5.833795402028135
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_196607.json	0.0006236034544624216	0.12617404993189252	-7.7236328125	5.419761663594935
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_65535.json	0.010875088685738516	0.11238070535165999	-10.8564453125	7.984475749177073
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_229375.json	0.0006669269474164934	0.12072373050015403	-7.642578125	5.317385951129698
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_32767.json	-0.05185006605558455	0.13759341370180952	-8.4853515625	5.046636050209962
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_98303.json	0.017161582357450415	0.10403567959445023	-9.5361328125	7.528634341290646
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model.json	-0.022733110973382046	0.11718634948507528	-9.2412109375	6.514663515572417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_163839.json	0.011150192865996868	0.11237567129741208	-7.9755859375	6.180424430494417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_131071.json	0.017154828989431107	0.10057427986289921	-8.3125	6.410593040039275
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_196607.json	0.008933176825091335	0.11148478014417737	-7.822265625	5.954880182836877
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_65535.json	0.008298997341466594	0.11313669715875802	-11.1669921875	8.544829184765133
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_229375.json	0.011126110100795927	0.11513740086044486	-7.5380859375	5.598419371694545
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv8/model_32767.json	-0.022733110973382046	0.11718634948507528	-9.2412109375	6.514663515572417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model.json	-0.003236519767745304	0.10387072689503955	-11.0322265625	7.988024271443436
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_65535.json	0.013345037472272964	0.11024934878821432	-11.662109375	8.97648239432001
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_229375.json	0.019315014801343944	0.10497704158618172	-7.9951171875	6.259600094705898
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv4/model_32767.json	-0.003236519767745304	0.10387072689503955	-11.0322265625	7.988024271443436
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_98303.json	0.015928391872716594	0.10149360048205994	-9.123046875	7.007564000175291
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model.json	-0.05185006605558455	0.13759341370180952	-8.4853515625	5.046636050209962
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_163839.json	0.002453001655467117	0.12276407613912008	-7.828125	5.819195572360067
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_131071.json	0.007392644384459814	0.11652508735289137	-7.994140625	5.833795402028135
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_196607.json	0.0006236034544624216	0.12617404993189252	-7.7236328125	5.419761663594935
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_65535.json	0.010875088685738516	0.11238070535165999	-10.8564453125	7.984475749177073
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_229375.json	0.0006669269474164934	0.12072373050015403	-7.642578125	5.317385951129698
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test2/results_new_adv16/model_32767.json	-0.05185006605558455	0.13759341370180952	-8.4853515625	5.046636050209962
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_98303.json	0.030617477002870562	0.09635251664016684	-11.35546875	9.000033060648914
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model.json	0.029808474482972334	0.09592542316503101	-11.3115234375	8.730537731742999
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_163839.json	0.031151247920472337	0.09510905743169518	-10.9306640625	8.631908303803453
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_131071.json	0.030965848855036535	0.09852152182063233	-10.857421875	8.624727327763555
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_196607.json	0.032041800544754695	0.09449366550401991	-10.18359375	8.291060484640125
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_65535.json	0.029089941610125257	0.09606381362160407	-12.3203125	9.749145470365274
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_229375.json	0.03158754097892745	0.09937327490420111	-10.9033203125	8.611256527100148
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv8/model_32767.json	0.024794417283729123	0.09258832055691689	-13.3896484375	10.100159065958012
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_98303.json	0.030609576836508348	0.09703536110267999	-11.3388671875	8.962563910050283
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model.json	0.0295440737539144	0.09570356012510253	-11.8193359375	9.03463264660058
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_163839.json	0.02924934657978862	0.09503524264397227	-11.046875	8.611728353494147
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_131071.json	0.0315541564049452	0.09762545919596041	-10.8955078125	8.661822401795794
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_196607.json	0.03131995469891701	0.09447150307051688	-10.2509765625	8.31980993338043
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_65535.json	0.030344666419298012	0.09227563663131538	-12.3779296875	9.696807082169169
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_229375.json	0.031706680584551145	0.09362477622187598	-11.2060546875	8.574667589957016
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv4/model_32767.json	0.02244959693860908	0.09880166810108036	-13.73828125	10.142628335194898
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_98303.json	0.030896276422233818	0.09732582323747047	-11.3330078125	8.983896418554366
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model.json	0.031405454886482255	0.09365583566088817	-10.9208984375	8.695398431372197
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_163839.json	0.03132364993802191	0.09694579665245014	-10.7802734375	8.63018195348348
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_131071.json	0.030324788581354387	0.09619119123182208	-10.759765625	8.533991223048472
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_196607.json	0.03236570736560543	0.09414515830418324	-10.447265625	8.39533168407856
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_65535.json	0.03305875583083247	0.09479522381436725	-12.2373046875	9.72880985387167
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_229375.json	0.0327121678871999	0.09611009443565105	-10.5078125	8.456572050177527
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test3_temp_0_1/results_new_adv16/model_32767.json	0.02238422943306367	0.09440689485604234	-13.3876953125	10.168938466337847
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_98303.json	-0.14628253849164927	0.25291177482809374	-16.669921875	9.505468902500102
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model.json	-0.07968031339705114	0.16031617815011862	-8.232421875	4.232348868775055
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_131071.json	-0.1815152417145094	0.2611544798803077	-15.4560546875	9.094771337670304
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_196607.json	-0.21902026214281056	0.24373875364771994	-17.107421875	7.726285769421908
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_65535.json	-0.10618205856928498	0.20124450577697095	-7.76953125	4.650857760163542
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_229375.json	-0.15295677742530012	0.2236738588306428	-14.05859375	6.758709974726015
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_32767.json	-0.10000234456550106	0.18020233624218476	-8.001953125	3.4823769626941212
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model.json	-0.01667788830082203	0.11948138134390338	-7.25390625	4.211913949288487
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model_65535.json	-0.060474881548473386	0.15642797099937214	-7.1630859375	4.56846406514156
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model_32767.json	-0.005530243875587161	0.10976627329373437	-6.8720703125	4.517786162221067
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv16/model.json	-0.1333029474246477	0.214617761177201	-7.919921875	3.4575316331013495
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv16/model_65535.json	-0.12525560860842902	0.22733761638999928	-7.6298828125	4.7096067861358755
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_98303.json	0.031362258815566285	0.09510124715897168	-10.34375	7.9877225125501194
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model.json	0.031362258815566285	0.09510124715897168	-10.34375	7.9877225125501194
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_163839.json	0.033355266913491645	0.09816450668801449	-10.3173828125	8.011701073294583
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_131071.json	0.03545046748597338	0.09898701830078734	-10.6630859375	8.123122658620252
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_196607.json	0.03499021908435543	0.09046767998229051	-10.244140625	7.518269729813144
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_65535.json	0.031630609627805326	0.08978833859059825	-10.498046875	8.061167288941641
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_229375.json	0.036162246990801145	0.09242226282107105	-10.01953125	7.453607123753803
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-10/model_32767.json	0.030773951265657618	0.09205124145186165	-11.705078125	8.512682036975567
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_98303.json	0.033083985394376306	0.09515419022093176	-9.8515625	7.720295739710607
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model.json	0.033083985394376306	0.09515419022093176	-9.8515625	7.720295739710607
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_163839.json	0.03576354343358559	0.09741079675902047	-9.84375	7.694673990007634
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_131071.json	0.03350664429475469	0.09379116529972181	-10.3212890625	7.982848796063839
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_196607.json	0.03493555503001043	0.09199633226882044	-9.9189453125	7.40883871299236
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_65535.json	0.03272452782489561	0.0902511351557286	-10.021484375	7.711188562512971
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_229375.json	0.036625680943371604	0.092013440230818	-9.767578125	7.2538165865991875
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-4/model_32767.json	0.033462938535686326	0.09186757023931168	-11.1708984375	8.479703062994604
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_98303.json	0.03281754591270876	0.09413039553328219	-10.16796875	7.936953067709513
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model.json	0.03281754591270876	0.09413039553328219	-10.16796875	7.936953067709513
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_163839.json	0.03438152400835073	0.09751412221549645	-10.1708984375	7.8342879166877735
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_131071.json	0.034593681701787574	0.09583439278076383	-10.5849609375	8.056114743727221
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_196607.json	0.03525385528118476	0.09083354445755479	-10.1298828125	7.509221257395276
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_65535.json	0.03293923395909446	0.08999106295006103	-10.3056640625	7.936597337234389
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_229375.json	0.0358872702325809	0.0922832253518331	-9.955078125	7.443795496932092
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-8/model_32767.json	0.03196866029488518	0.09211574082629227	-11.517578125	8.45979020924996
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_98303.json	0.03208270301898486	0.09577490200230919	-10.2431640625	7.942324576357258
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model.json	0.03208270301898486	0.09577490200230919	-10.2431640625	7.942324576357258
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_163839.json	0.03350766367105949	0.09877790016287333	-10.234375	7.920734631924932
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_131071.json	0.036356183332789664	0.09715172706402202	-10.58984375	8.066843208503927
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_196607.json	0.03540472297429541	0.09024430559295868	-10.1669921875	7.468321400878109
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_65535.json	0.03208410466140396	0.09023265480104524	-10.4658203125	8.01383104382432
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_229375.json	0.03574379301768006	0.09243189308775826	-10.0244140625	7.465440535631655
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-9/model_32767.json	0.031138633138700418	0.09174499390648751	-11.5966796875	8.506111584503515
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_98303.json	0.03380914421320459	0.09375668590356948	-10.015625	7.884031898995272
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model.json	0.03380914421320459	0.09375668590356948	-10.015625	7.884031898995272
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_163839.json	0.03422836271855428	0.09689138546239809	-9.9462890625	7.662436652116145
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_131071.json	0.033274481341336114	0.0959693180113882	-10.390625	7.933546628675916
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_196607.json	0.034269010348708245	0.09281324006635346	-10.009765625	7.431451213092121
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_65535.json	0.03212322322710073	0.09044611665741614	-10.2568359375	7.885004319194029
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_229375.json	0.03471587943632568	0.09269754647096759	-9.806640625	7.314617404697228
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-6/model_32767.json	0.03276836100600209	0.09117451373713145	-11.2373046875	8.448449779266639
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_98303.json	0.03111034544624217	0.09481981774821431	-10.4375	8.050863695902446
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model.json	0.03111034544624217	0.09481981774821431	-10.4375	8.050863695902446
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_163839.json	0.033352973316805846	0.09877594983071226	-10.38671875	8.015540287990476
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_131071.json	0.03453761600502349	0.09656309761890751	-10.740234375	8.172989428297846
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_196607.json	0.034271303945394044	0.09185972204160071	-10.26171875	7.538563576431417
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_65535.json	0.030910547690501042	0.09099705056448726	-10.5830078125	8.133946056685154
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_229375.json	0.03575564326722338	0.09231872561151802	-10.154296875	7.511814983701691
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-11/model_32767.json	0.03093972733722599	0.09205954643101144	-11.7666015625	8.576016804547
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_98303.json	0.03348268895159186	0.09441819555872939	-9.91796875	7.7823862984963315
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model.json	0.03348268895159186	0.09441819555872939	-9.91796875	7.7823862984963315
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_163839.json	0.03526889108168058	0.0972810268333145	-9.974609375	7.689109323657852
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_131071.json	0.03346293853568632	0.09552226363588187	-10.3701171875	7.952540228129442
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_196607.json	0.034931350102753125	0.09200569562910049	-9.9501953125	7.3562035337939795
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_65535.json	0.032446875203875264	0.09055764282293881	-10.1494140625	7.792608404791507
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_229375.json	0.03616925520289666	0.09359786202426644	-9.79296875	7.305559565257369
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-5/model_32767.json	0.033029831028183715	0.09115199650322828	-11.2431640625	8.455215900626577
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_98303.json	0.03262717738778706	0.09482098938695435	-10.123046875	7.905724790716708
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model.json	0.03262717738778706	0.09482098938695435	-10.123046875	7.905724790716708
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_163839.json	0.03483642068436847	0.09694008610746492	-10.0244140625	7.704401494668632
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_131071.json	0.03403671997325156	0.0956492854477821	-10.4453125	7.9500968879217915
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_196607.json	0.03483119638080637	0.09066109978921234	-10.05859375	7.493257670897281
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_65535.json	0.03176363823558194	0.09082620185184148	-10.2958984375	7.9329060754672405
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_229375.json	0.03513509794167537	0.0928402458288811	-9.8291015625	7.349073387955794
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-7/model_32767.json	0.03235309258383351	0.09156561646269108	-11.4912109375	8.51113246738531
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-3/model.json	0.032975676661991124	0.09634142555694104	-9.7685546875	7.674922858232634
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_dt_test2/results_new_r_to_go_-3/model_65535.json	0.033805576396137786	0.09120489612809468	-9.9365234375	7.71848898998458
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_98303.json	-0.14628253849164927	0.25291177482809374	-16.669921875	9.505468902500102
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model.json	-0.07968031339705114	0.16031617815011862	-8.232421875	4.232348868775055
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_131071.json	-0.1815152417145094	0.2611544798803077	-15.4560546875	9.094771337670304
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_196607.json	-0.21902026214281056	0.24373875364771994	-17.107421875	7.726285769421908
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_65535.json	-0.10618205856928498	0.20124450577697095	-7.76953125	4.650857760163542
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_229375.json	-0.15295677742530012	0.2236738588306428	-14.05859375	6.758709974726015
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv8/model_32767.json	-0.10000234456550106	0.18020233624218476	-8.001953125	3.4823769626941212
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model.json	-0.01667788830082203	0.11948138134390338	-7.25390625	4.211913949288487
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model_65535.json	-0.060474881548473386	0.15642797099937214	-7.1630859375	4.56846406514156
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv4/model_32767.json	-0.005530243875587161	0.10976627329373437	-6.8720703125	4.517786162221067
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv16/model.json	-0.1333029474246477	0.214617761177201	-7.919921875	3.4575316331013495
/home/gaoqitong/Dropbox/RLHF/VisDial/Implicit-Language-Q-Learning/outputs/visual_dialogue/visdial_hard_yn_cql_official_test4_temp_10/results_new_adv16/model_65535.json	-0.12525560860842902	0.22733761638999928	-7.6298828125	4.7096067861358755
