Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.961017370223999	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
41.0508713722229	50	27.56613968910082	6.24797694408488	37.982340661925264	12.538335726829246	100000	1.8186299050999482	0.5
71.66764426231384	100	36.568241914760875	7.478495957369476	47.26189966779202	24.071876746602356	200000	1.8341939488689072	0.5
102.52503848075867	150	37.79861981078648	3.446176349264969	45.934511070139706	30.022896006703377	300000	1.8463045341364526	0.5
132.64005279541016	200	39.32232613867694	3.3319237248623566	47.012608473654836	32.94601393910125	400000	1.848808314325543	0.5
162.20416617393494	250	109.62327865490592	10.01497237458285	122.28189963434124	80.80453473093803	500000	1.849420665081283	0.5
191.05219841003418	300	142.53444034709116	12.79654914983264	153.70018343708944	115.23864859191235	600000	1.8511404582593318	0.5
222.19386100769043	350	199.8278278426434	9.947629471978424	217.11706625530496	183.35364345950074	700000	1.8512674424105404	0.5
250.12073469161987	400	259.60417965314554	8.370080991654751	268.5367937600822	236.76639390498167	800000	1.8505178770308925	0.5
278.00421595573425	450	316.89024199723576	2.675555474206293	322.71557991660666	310.74234659655485	900000	1.852682802248297	0.5
306.76866388320923	500	341.4726925324062	2.2921578543197256	346.9863229196053	336.8320425535494	1000000	1.853255659514107	0.5
309.9562032222748	501	344.37352566967036	3.20809265634998	349.0940143329208	334.55332504748367	1002000	1.8535389867259346	0.5
