Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.43057107925415	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
40.10654139518738	50	94.3182759406717	7.315371185787956	112.86543458104279	79.55343284909031	100000	1.8186299050999482	0.5
68.724600315094	100	206.32029548192855	6.077355190710074	221.7093830226222	192.63993383462184	200000	1.8341939488689072	0.5
98.09449553489685	150	221.48239153886203	8.946870187916796	240.6855419118947	211.0718330336531	300000	1.8463045341364526	0.5
126.96749210357666	200	245.71361221390103	9.40886230132309	266.8337619348604	232.50848651799606	400000	1.848808314325543	0.5
157.4581925868988	250	263.12069481680425	6.943361110459224	277.5578490784392	252.77939271833748	500000	1.849420665081283	0.5
187.49148035049438	300	273.819750511178	3.828254732929117	278.6708761247428	254.40379691712587	600000	1.8511404582593318	0.5
216.14706254005432	350	264.0588395219849	2.732530403009525	274.43190766940825	256.3270080165821	700000	1.8512674424105404	0.5
244.66206693649292	400	272.4023407010965	5.50816027641821	286.6419313829392	263.7328879740089	800000	1.8505178770308925	0.5
273.29379510879517	450	276.4326063224415	3.7381518207540365	282.7849598968751	265.9314001775929	900000	1.852682802248297	0.5
302.0304625034332	500	273.81205695789924	3.54955332263225	283.5677170600975	264.00942520808894	1000000	1.853255659514107	0.5
305.61825919151306	501	264.5682116413291	8.567728055405565	287.331218640702	257.2132879481651	1002000	1.8535389867259346	0.5
