Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.237828731536865	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
35.41938900947571	50	50.113153860808126	22.568653451999428	78.65917483305202	-1.2654428236419335	100000	1.8186299050999482	0.5
61.87999248504639	100	128.97155331125165	3.943695381351562	136.90707297599874	117.15746840881184	200000	1.8341939488689072	0.5
88.23988008499146	150	235.85321695687463	5.187350893185628	246.4682469352265	222.87894886895083	300000	1.8463045341364526	0.5
114.0205249786377	200	281.2664416994679	2.755416471168133	290.185930782156	275.2763617365272	400000	1.848808314325543	0.5
140.42001581192017	250	312.0934849961939	2.4825349754715478	317.3584884064039	306.78165908367373	500000	1.849420665081283	0.5
166.39517092704773	300	329.8774514767093	2.189064244496556	336.2569609984057	324.52354473189916	600000	1.8511404582593318	0.5
192.50696897506714	350	340.79351606972574	2.084961621380315	345.3647522257579	334.25383041649184	700000	1.8512674424105404	0.5
218.31884765625	400	345.5334020324634	1.8001311378931726	350.194207973258	341.30303526110947	800000	1.8505178770308925	0.5
244.4102213382721	450	346.0191781795223	1.9394473912798964	352.290528409183	341.8945298297331	900000	1.852682802248297	0.5
274.4708585739136	500	346.1102363147938	2.024162690027687	351.25478670291704	337.2152192258018	1000000	1.853255659514107	0.5
277.75703740119934	501	350.35012473847354	1.993382142668162	354.4016163054621	345.09550168772694	1002000	1.8535389867259346	0.5
