Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.856729507446289	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
36.436028718948364	50	-0.21762687645948034	1.2348840275554807	4.214186042361007	-2.2319244630416506	100000	4.60146463213413	0.5
64.18278694152832	100	187.3237344000476	332.2981757247213	802.0134957605042	-1.6120572360573533	200000	4.646345710132934	0.5
95.18746590614319	150	1490.7026395516305	8.718340074708939	1505.187417268753	1461.8976831098553	300000	4.667544207091623	0.5
122.78911900520325	200	2229.255164592165	31.37150038905247	2298.0065917799366	2111.213393241167	400000	4.67830083346032	0.5
150.09700393676758	250	2021.7768920024898	34.98640787119245	2103.2969091851846	1936.3491134886863	500000	4.683113861235732	0.5
177.3549726009369	300	2528.223492814063	205.72801030835367	2705.355326946825	2008.598707774654	600000	4.684742291695828	0.5
205.96110892295837	350	2565.760372014275	48.50318232986556	2712.146037466475	2478.035530857742	700000	4.686085195024968	0.5
232.6446602344513	400	3435.5727502253535	34.66009664911141	3489.319203712046	3302.688429598522	800000	4.689393900542693	0.5
258.90946340560913	450	3702.5254233325772	401.17209068438683	3895.636735578999	-248.7586570632775	900000	4.6919209604959535	0.5
285.61957335472107	500	3500.164083261306	48.76262512764762	3593.3993332087994	3272.4096625717357	1000000	4.692440002618602	0.5
288.580997467041	501	3174.7030214845495	898.5763590430661	3563.995865610428	-201.27176440325275	1002000	4.692488396238485	0.5
