Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.437460899353027	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
81.54961109161377	10	173.45921288450256	3.427543394415922	179.7747802739177	163.9616236148504	1000000	0.9090909090909091	0.637731943263464
149.56846952438354	20	255.64821914773313	2.767438738821548	261.6043236651458	249.67049409943866	2000000	0.9523809523809523	0.637731943263464
216.9831531047821	30	309.31067235172645	2.9202626282991537	314.9806553495	301.7156379730295	3000000	0.967741935483871	0.637731943263464
283.3674509525299	40	335.11470908621027	2.6203265908755573	340.58352785455645	329.2198386775708	4000000	0.975609756097561	0.637731943263464
349.8684058189392	50	345.2846241146794	2.129716260503298	349.79995150028844	339.40385650850294	5000000	0.9803921568627451	0.637731943263464
415.8969943523407	60	349.8165998930586	2.8795509244159514	354.75982435694095	341.9537101984024	6000000	0.9836065573770492	0.6592264779932553
483.62931537628174	70	349.9743662207522	2.129136811138407	354.9083800968074	344.0969123095274	7000000	0.9859154929577465	0.7137669727197745
551.5196936130524	80	352.3286581308951	2.2076723200032586	357.6222411438357	346.7088507878361	8000000	0.9876543209876543	0.7137669727197745
618.4403486251831	90	354.3507946143429	2.3359031331879385	358.7121562883258	349.7929896247806	9000000	0.989010989010989	0.7137669727197745
682.3968801498413	100	355.308560967749	2.5436512107440206	359.7124991414603	348.7137451337767	10000000	0.9900990099009901	0.7137669727197745
