Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.18565583229065	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
86.47318696975708	10	183.85434374352582	4.465650172765429	193.0272424246141	173.83734558298602	1000000	1.5816428935639566	1.7853566569364354
153.85441255569458	20	324.8510929422553	2.6850333598396046	331.39087201748043	317.9852495432133	2000000	1.8863138807303454	1.7853566569364354
221.16960096359253	30	348.1238541186166	2.3113628606193393	353.36486540347687	340.0387664838199	3000000	1.9337550354999622	1.7853566569364354
289.4459648132324	40	351.63817772224786	2.218773636463954	356.14052866143174	341.71647046040744	4000000	1.8128884888382903	1.7853566569364354
357.14273476600647	50	354.0613627402556	2.1676931833440474	358.82421204587445	348.9374667296652	5000000	1.7472493730031615	1.7853566569364354
424.342853307724	60	354.3844963032975	1.9725769808184852	358.53165546170203	349.6332589889207	6000000	1.6698973924417737	1.7853566569364354
492.48540592193604	70	353.1799183430262	1.7792539933923228	357.63759567937814	349.7579682460928	7000000	1.6050180420171154	1.7853566569364354
559.3293251991272	80	355.4622453267794	1.9615128788054172	359.756460974575	350.18396447692066	8000000	1.5561315618306872	1.7853566569364354
626.0501289367676	90	357.0567023997096	1.8475965263968732	360.54413496376947	351.9044954048004	9000000	1.5126243266737731	1.7853566569364354
694.1315681934357	100	354.12541474566405	1.5988292782006177	358.8663229008671	351.24819753061456	10000000	1.4897988448756214	1.7853566569364354
