Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.046586990356445	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
38.56309986114502	50	302.81824857208903	3.6636433457371216	311.3602067140164	291.8165638629798	100000	4.610406805065743	0.5
66.16945624351501	100	1006.429532333654	6.489413300553818	1019.1086319517344	988.6119857057929	200000	4.653935880017789	0.5
95.56557512283325	150	1684.8371469493968	16.064250975422993	1713.2518205187516	1641.7414765432477	300000	4.6749685865362824	0.5
123.00508117675781	200	2319.9582301564706	574.1295368753597	2682.4778153412044	19.211495428404305	400000	4.68526352105535	0.5
152.39380836486816	250	2519.7002183193376	22.983664937890392	2573.804763117805	2415.464457848342	500000	4.687991889179126	0.5
180.160635471344	300	2958.075636992225	215.6303765234751	3209.8224080726504	1416.4551303242333	600000	4.691707158144372	0.5
208.98366498947144	350	2702.740796986878	495.82327777305966	3031.789358441718	145.69517559930682	700000	4.694911840223484	0.5
236.02344822883606	400	2681.4333754713625	155.37395805065307	2858.6561766127124	1347.7282367127482	800000	4.696122671456811	0.5
264.46349120140076	450	2996.8675778718916	251.5465341833249	3271.9191309660673	1053.1643798975274	900000	4.697316876105876	0.5
293.9120616912842	500	3128.137446013969	100.14985782097618	3347.1121981330216	2798.19310119655	1000000	4.696991953493721	0.5
298.1578025817871	501	3110.0596854608357	412.34075239313813	3361.7792144715786	-135.10968488780782	1002000	4.697146672553556	0.5
