Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.130503177642822	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
36.170851945877075	50	25.67670519126011	9.976208805926506	43.242039531935006	12.945245082257316	100000	1.8186299050999482	0.5
64.38869571685791	100	33.15810070023136	4.303618958211381	41.308830393478274	26.642123153273133	200000	1.8341939488689072	0.5
92.90774989128113	150	32.42351352260284	4.418794637560689	41.01217015029397	23.022487289039418	300000	1.846304534136453	0.5
122.2740888595581	200	30.823469570012932	3.5419467167379595	36.93314426553684	23.290720934048295	400000	1.8488083143255432	0.5
150.65933322906494	250	54.13146515275541	23.31661917322205	96.5136282852909	28.129170333966613	500000	1.8494206650812832	0.5
177.36330318450928	300	100.24253263126893	20.88064743027178	148.35349458182463	62.893409425159916	600000	1.851140458259332	0.5
203.71771097183228	350	199.90414852878686	3.728841366599617	206.73146671248105	189.37775564030744	700000	1.8512674424105406	0.5
229.88106894493103	400	236.46889617808264	2.9243056727223644	244.1104873138829	228.28046644471033	800000	1.8505178770308928	0.5
255.68672704696655	450	269.6219764339173	2.884438937644035	276.3763281972351	262.3668305578467	900000	1.8526828022482973	0.5
281.8735227584839	500	286.2620649019636	2.6282705176621097	292.44369758758694	280.4309487111168	1000000	1.853255659514107	0.5
285.2452039718628	501	288.9666042906177	2.580052727492189	293.3708012333809	282.825558055687	1002000	1.8535389867259346	0.5
