Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
7.96182918548584	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
35.790125608444214	50	27.250010539364062	11.670712426914882	38.71359551185742	-20.46468922542408	100000	1.8186299050999482	0.5
64.0477237701416	100	36.971865422866216	4.054338663245815	44.34721924140467	25.863826674059965	200000	1.8341939488689072	0.5
92.42745757102966	150	146.3640342094919	4.463969755801364	155.27845313865691	135.9630056580936	300000	1.8463045341364526	0.5
120.6163067817688	200	216.26970787082388	2.9568173123734636	220.2547991843894	204.28137027972843	400000	1.848808314325543	0.5
146.77414321899414	250	273.1802109897038	2.1182712485751383	277.69508793337445	268.37804755044635	500000	1.849420665081283	0.5
172.7675724029541	300	322.82794451958523	2.0217910327316333	326.84895353746833	317.4144448211882	600000	1.8511404582593318	0.5
199.10275387763977	350	336.9887271712576	2.1380794311009956	340.8905184403993	331.09056052559754	700000	1.8512674424105404	0.5
225.94271063804626	400	349.75907990243667	1.694089931436675	354.5041569028981	344.6283687053947	800000	1.8505178770308925	0.5
253.38620948791504	450	353.013159711465	2.639198546281124	357.4533504040446	345.3308487958275	900000	1.852682802248297	0.5
279.9739148616791	500	352.6538316672268	1.8932788888428576	356.92826919071376	347.1220018272288	1000000	1.853255659514107	0.5
283.29173493385315	501	351.0804661962944	2.0244109259701686	356.0428858550149	346.64741138380487	1002000	1.8535389867259346	0.5
