Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.34109616279602	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
37.4502694606781	50	-251.46247903813534	18.03730337936584	-224.2812317981152	-396.8386748706689	100000	19.664550254806073	7.2809213982718495
64.21989607810974	100	-1284.7165674198127	68.36221090310922	-1044.1494729391125	-1378.5547763537616	200000	19.911541175478522	7.2809213982718495
92.83651781082153	150	-620.5780530262587	16.653278888316255	-586.817256256938	-678.8344804852968	300000	20.036334748640968	7.460145164858131
122.70546221733093	200	-1608.1495195996959	890.5039382091743	-841.1017437502742	-2867.406012535095	400000	20.098869435493896	8.829890616144073
153.11264419555664	250	-1007.4159422129044	374.0596342462748	-900.7925156354904	-4683.9851066321135	500000	20.177382324445297	8.829890616144073
181.64421105384827	300	-2576.563612728592	2114.880365892247	-1467.5469896290451	-8364.555452928413	600000	20.20021370975892	8.829890616144073
210.4752972126007	350	-5288.5410809502655	203.6979935082128	-4565.324849271914	-5722.826065711444	700000	20.211663812808702	8.829890616144073
239.7849395275116	400	-6269.941558930266	809.3511796766763	-4376.626111317426	-7818.322786077857	800000	20.222138941526236	8.829890616144073
267.3461215496063	450	-3981.5797405943144	1459.8053299436472	-2184.7311567142606	-5815.826993338764	900000	20.22628052432298	8.829890616144073
295.04481530189514	500	-5574.5109698393035	1623.991356504071	-1674.6505734920502	-8044.327457018197	1000000	20.22941698969033	8.829890616144073
298.7637014389038	501	-5691.13204944046	1618.3823039541164	-1675.396677494049	-8334.29616998136	1002000	20.230480928706136	8.829890616144073
