Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.944109678268433	0	-0.30404523389316856	0.7831634747396644	2.251814016645012	-1.870696566842263	0	0.0	0
36.474456548690796	50	1199.5900030235534	146.7952010063798	1395.1440018620924	661.8993520148215	100000	19.733735458322382	8.240323501043735
64.31879782676697	100	914.9549306545631	203.73259710660724	1134.1724214348942	-109.09982552734436	200000	20.034140482937627	8.49237141956883
95.0478003025055	150	663.3496190334575	184.27986193953524	846.3419078498846	-16.211870572813496	300000	20.03169310418538	8.49237141956883
123.95041394233704	200	603.9216530406236	861.3394371919784	970.9948805300519	-3818.674490634352	400000	20.069889561525248	8.49237141956883
153.53616452217102	250	359.88034240990515	461.96802077208326	992.7674796463689	-2406.714102605125	500000	20.10107757862734	8.49237141956883
180.94845700263977	300	533.972967300791	108.89437184950587	771.200870277069	88.33917893649777	600000	20.09778362961003	8.49237141956883
207.70114660263062	350	348.8688336850602	74.39618438919713	540.8934397333069	-22.42953905565082	700000	20.10324519285234	8.49237141956883
234.40792512893677	400	797.925397442677	353.8039528861404	1047.9912039253977	-834.7284756824374	800000	20.109119423080116	8.49237141956883
261.90472292900085	450	-466.847883859147	929.7892420223138	1301.8207429030444	-7406.310483205132	900000	20.120334905598675	8.49237141956883
289.5228998661041	500	403.515559960202	951.9396971561292	1001.4412549167755	-1872.5920528322458	1000000	20.112496356542795	8.49237141956883
293.507465839386	501	758.5598620192319	664.3841488463202	1108.9178877107333	-1937.4682402322069	1002000	20.115073931574077	8.49237141956883
