Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.733241081237793	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
36.28670382499695	50	139.2485095265473	17.26288231360089	178.4179958308814	100.57943326912209	100000	19.664550254806066	7.2809213982718495
63.81287980079651	100	-439.2592721607354	292.9965324759384	274.7255849070534	-810.9808071576699	200000	19.91154117547852	7.2809213982718495
94.52253222465515	150	-173.17230214355092	154.71462016282817	75.59642923536012	-1255.022843136103	300000	20.036334748640964	7.460145164858131
123.72632431983948	200	-203.43661957545325	29.31735007544733	-142.05802500294521	-282.8082106281072	400000	20.098869435493892	8.829890616144073
151.3845624923706	250	-1160.4958498352423	527.0521665740785	-578.694335520966	-2249.8806325420737	500000	20.177382324445297	8.829890616144073
179.1137411594391	300	-741.6691853381448	1039.5249863155466	-258.70796373905614	-7023.371304601431	600000	20.20021370975892	8.829890616144073
206.90612602233887	350	-783.295022696529	135.1409794586295	-607.2393961164635	-1226.2663980163634	700000	20.211663812808702	8.829890616144073
236.50739789009094	400	-576.0665052018429	811.4002346093099	-308.80311668722425	-4931.270559720462	800000	20.222138941526236	8.829890616144073
265.22244000434875	450	-1158.1539894581217	870.6936643624357	-713.8148544792784	-4798.372110051103	900000	20.22628052432298	8.829890616144073
294.42161440849304	500	-444.1653790861096	49.26490348510735	-367.0248441819567	-592.4608270765748	1000000	20.22941698969033	8.829890616144073
297.61032795906067	501	-561.6989438758187	64.46293255200014	-446.517728208506	-802.6264874800108	1002000	20.230480928706136	8.829890616144073
