Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.166143655776978	0	-0.813261981599876	19.297677396125206	29.944989854469895	-27.727565122768283	0	0.0	0
87.13615584373474	10	69.3790752473973	3.6850466618094697	77.51404287078185	57.88174333196366	1000000	0.8918948990968406	0.7965523035719173
155.07414317131042	20	227.19479790768906	4.03889137593032	234.9314767724136	216.82348183715658	2000000	0.9433735185745356	0.7965523035719173
224.41067123413086	30	306.74779247465193	3.0242730703445284	312.0976460996899	299.440028768935	3000000	0.9605230352012798	0.7965523035719173
292.81896471977234	40	332.9381595148916	2.518538416327562	339.27444133500103	325.07000371883623	4000000	0.9687494401825598	0.7965523035719173
363.8249623775482	50	346.2694543834036	2.508206920831193	351.6015136406204	339.31878544186475	5000000	0.9748770009310775	0.7965523035719173
431.8405022621155	60	350.9162191197678	3.024929222306794	356.3900523930206	342.24951097375015	6000000	0.9609507464843223	0.7965523035719173
500.8514575958252	70	351.9319967325228	2.45375850922023	356.9673012900239	346.2739638732746	7000000	0.9556820779026307	0.7965523035719173
570.5211119651794	80	353.88577306732134	2.555687088701529	358.7384824242181	345.66035218077013	8000000	0.9348882259177765	0.7965523035719173
640.9291994571686	90	355.5408233246986	2.245773502774158	359.899864652456	349.84681774815544	9000000	0.9253591657743919	0.7965523035719173
711.0016996860504	100	353.74675061857636	2.098681069566606	358.1107881143689	348.33887247380335	10000000	0.912721693470439	0.7965523035719173
