Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
10.40200138092041	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
40.233683824539185	50	148.70662539577745	7.835267640627851	159.32533425083966	116.14391241583508	100000	1.8224481875398229	0.5
68.29393172264099	100	289.6285308960862	4.471654178463029	301.81854581518564	279.76048650604207	200000	1.8389749983382693	0.5
97.40576171875	150	336.8439882731038	2.4949921746325217	343.0411231526232	330.4143423512578	300000	1.8447225778001188	0.5
126.17937421798706	200	340.9570139763529	2.0468696589544235	347.7599225892027	337.4353978935178	400000	1.848710227447018	0.5
155.4591338634491	250	342.6578602423669	2.171315190713483	348.43620291290426	338.32848833245225	500000	1.8486372099645916	0.5
181.91835522651672	300	346.1960239863406	2.4994842778428112	351.52902843712945	337.65003693959443	600000	1.853298418196664	0.5
207.98340892791748	350	349.5501445398385	2.4862008445664494	354.52265474080923	338.7677075044485	700000	1.855345722707094	0.5
233.7097716331482	400	351.1289133164994	2.4406450516555274	355.7861613983987	343.42961659666616	800000	1.8572875590170084	0.5
259.68009996414185	450	351.94976357722504	2.3486531972755373	356.6984636115667	345.9306797167228	900000	1.8599517027491819	0.5
285.84782695770264	500	352.5611200083611	2.0972090268057366	357.44317483878694	347.8656975972699	1000000	1.8589356529636014	0.5
288.9568362236023	501	352.322648211234	2.0742610560965207	356.21820854756515	347.46667381119914	1002000	1.8590958766967167	0.5
