Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.090321779251099	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
37.45307660102844	50	26.61790519818078	2.443163702885243	31.90759485180024	18.7825691687176	100000	7.8352010171864706	6.051690688497223
66.59741115570068	100	26.569812469865354	4.412790039394078	35.748083376092836	10.17527289440659	200000	7.829581580172182	6.5955395471529155
96.79245495796204	150	27.90198880181453	6.112993499409938	35.58722888272314	-3.570386561928899	300000	8.028121073164726	7.768367627135068
125.95852661132812	200	26.0341829203618	6.628329316616533	33.740018364973366	-9.185850833076984	400000	7.97609697323165	7.768367627135068
155.34562039375305	250	12.487203562813338	14.82763634463425	39.40059083068627	-8.77115118689835	500000	7.951998589445974	7.768367627135068
182.91556096076965	300	145.7646108574935	24.657901976793767	171.06281274626963	-2.886981545118033	600000	7.983674733801793	7.768367627135068
209.45557141304016	350	194.093748186745	6.826119470028668	219.39532529585995	179.1807237099856	700000	7.978058148178504	7.768367627135068
235.98208618164062	400	255.22103826279323	2.0135163619852205	262.1677020841744	250.35942091022298	800000	7.948499571930373	7.768367627135068
262.33261609077454	450	347.2083350900303	3.6713189539531497	355.0303348413436	340.57377921577427	900000	7.937383750596724	7.768367627135068
288.50708198547363	500	341.9363675001655	3.045110611573907	346.7092306604609	331.1065599572612	1000000	7.897944917091887	7.768367627135068
291.93377208709717	501	322.10427951738546	6.783345159462291	338.94734993271413	303.9189771913225	1002000	7.896380491492582	7.768367627135068
