Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.475706338882446	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
35.7062087059021	50	28.53852611331392	4.889839739680273	36.85037515372596	13.149394001229666	100000	1.8287196216634354	0.5
63.827088594436646	100	29.898832221182246	3.2304924483066566	37.27582008729223	22.53853841405362	200000	1.8559943367649339	0.5
92.12436819076538	150	37.113883374823835	3.2760722212666136	45.47102194512263	30.151046147104353	300000	1.862781364413194	0.5
120.18993616104126	200	38.57554714469821	2.8525917663198217	45.09388635121286	33.35487607866526	400000	1.867454476295365	0.5
149.08143663406372	250	39.61115294601099	4.050441922890367	47.878435072954744	31.277914870530367	500000	1.8725317301787296	0.5
176.47852492332458	300	37.79252567577394	2.737215356980168	42.78579400666058	29.819448177702725	600000	1.8695275068587118	0.5
205.9043207168579	350	37.96480312369057	6.568179908829778	48.50244408240542	22.518882148200646	700000	1.8680911725551956	0.5
235.57867908477783	400	75.99381339128067	31.49814497184518	122.53972288736259	32.24628795237686	800000	1.8682045054007987	0.5
263.01823568344116	450	97.90737166516523	6.521186384302615	114.01188948727213	74.66279264344485	900000	1.8682299252293924	0.5
289.8280940055847	500	137.96243081902378	7.426925481936739	155.22060746329953	127.33996871493582	1000000	1.8675519300746202	0.5
292.95599246025085	501	136.44658748638656	3.3499726514292476	147.07096128165722	128.39818473043852	1002000	1.8673619584885637	0.5
