Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.572969198226929	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
35.77564334869385	50	2.969220488749903	38.07373880077309	34.27581429117163	-146.44112348373164	100000	19.733735458322382	8.240323501043736
63.23311257362366	100	-319.2212395144705	79.52013109583626	-108.79394213523483	-474.13683173363097	200000	20.034140482937627	8.49237141956883
92.0199728012085	150	-475.02569346742274	223.39201282555857	57.94643384311348	-800.2108207332785	300000	20.03169310418538	8.49237141956883
122.29998660087585	200	118.76026306103704	92.14011056662191	287.94628516526427	-221.30943276314065	400000	20.069889561525248	8.49237141956883
150.59201502799988	250	-241.29760357204262	79.11568567727423	-86.14709830028005	-482.1304259184981	500000	20.10107757862734	8.49237141956883
177.9227237701416	300	-1048.767385627448	1372.8920213221008	-470.61689368983207	-11339.297919154895	600000	20.09778362961003	8.49237141956883
205.38281297683716	350	-1255.6684691864295	256.1753068387715	-955.7791088190861	-3192.0050713168457	700000	20.10324519285234	8.49237141956883
232.66924738883972	400	-1570.5774188420194	331.0965927996424	-887.0623851432465	-2464.485281256959	800000	20.109119423080116	8.49237141956883
259.62432384490967	450	-1475.9571168296472	221.4017150884648	-1101.6655642467376	-2095.7610506075434	900000	20.120334905598675	8.49237141956883
288.80131459236145	500	-4330.1520065201385	2098.574212258534	-1137.3651159416768	-7930.6594104245305	1000000	20.112496356542795	8.49237141956883
292.05145025253296	501	-4057.2895359665995	2125.25478388546	-1264.7098333371396	-7472.435908228159	1002000	20.115073931574077	8.49237141956883
