Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.716114044189453	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
39.121787548065186	50	27.213904274867264	4.899030575407756	35.825582474295516	11.523512153420597	100000	1.8186299050999482	0.5
70.00621056556702	100	29.92673191017805	2.8866664187412305	35.5409403630689	23.818384409795016	200000	1.8341939488689072	0.5
101.50865483283997	150	31.739064718206464	2.8159337349202933	37.71203410979797	25.56895189092029	300000	1.8463045341364526	0.5
132.31695175170898	200	33.769659251100904	3.1427055762733636	40.74392759066541	25.82042629085481	400000	1.848808314325543	0.5
162.8349847793579	250	35.234865209829586	2.4630793478190665	40.78785095107742	28.255283882142976	500000	1.849420665081283	0.5
193.2501926422119	300	45.23635609249199	2.903517565907772	51.26398033555597	38.83004769962281	600000	1.8511404582593318	0.5
225.36899948120117	350	45.35316043316867	3.415536698865718	52.922100270632654	35.60828731069341	700000	1.8512674424105404	0.5
260.9808626174927	400	44.41966304184356	3.2216568489944	51.17209044331685	38.01035179197788	800000	1.8505178770308925	0.5
299.93099427223206	450	44.70622602128846	3.1755367107567603	51.05803774949163	35.45003858488053	900000	1.852682802248297	0.5
336.9287226200104	500	44.937932126006345	3.300367501777508	53.99767904682085	36.01673441659659	1000000	1.853255659514107	0.5
342.06551575660706	501	46.60048183645209	3.053515703880406	53.379674824886024	39.89853968145326	1002000	1.8535389867259346	0.5
