Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
16.065062999725342	0	-0.3023757225339068	20.43353154720061	29.695772328414023	-28.46130512468517	0	0.0	0
72.26234078407288	10	341.2407312772058	2.7411895559678823	348.38694108556956	334.86891081003705	1000000	3.2695232542563275	3.0646478347432238
128.99582386016846	20	349.6594192698034	2.8420884855437096	355.514057653294	341.37781685218215	2000000	3.064555525181142	3.0646478347432238
177.97957611083984	30	351.39645346544336	2.6211616126843382	356.1873826106312	341.987552859413	3000000	2.8765871626203947	3.0646478347432238
231.081933259964	40	351.7412242028002	2.5016274541639527	358.0287492566422	344.25583318286226	4000000	2.82247477455583	3.0646478347432238
285.91522789001465	50	349.4268800579526	2.3693462864326484	356.68138724239543	343.83882293407805	5000000	2.790105136084992	3.0646478347432238
339.66929173469543	60	352.78052552087365	2.0635514259803323	356.71959114808124	348.3738331377972	6000000	2.779751527598867	3.0646478347432238
391.8642244338989	70	355.472676859334	2.7173978252844146	360.3143591209664	347.558860879275	7000000	2.7760363342809997	3.0646478347432238
446.46355652809143	80	353.25100846792395	5.155189243354543	361.94662825984415	338.68032025845605	8000000	2.722922735127424	3.0646478347432238
498.33480763435364	90	354.27533816343305	3.0366243146782916	359.6145687918179	345.1376749286719	9000000	2.686590406950572	3.0646478347432238
550.5904529094696	100	354.44553931062086	2.48542354011369	359.25408758048434	349.02012958351406	10000000	2.673275629669385	3.0646478347432238
