Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.622623443603516	0	-0.30152912016587186	0.7031112561796045	1.3895061342589152	-2.04430108904604	0	0.0	0
37.39031529426575	50	0.33199142790946984	0.7084989630670808	2.7404082065350757	-1.2710102048637282	100000	0.980392156862745	0.09901475429766744
65.3612368106842	100	2.901087490706753	1.557028383121593	5.781043478920566	-0.36977598663187905	200000	0.99009900990099	0.09901475429766744
93.81014156341553	150	231.838707646082	11.866464420512166	247.03479745332152	202.18928369646892	300000	0.9933774834437085	0.09901475429766744
121.62565541267395	200	522.7213369569845	3.4534034624149608	536.8766558286152	515.59290182736	400000	0.9950248756218905	0.09901475429766744
149.82500958442688	250	946.5095063046549	3.8191058728290375	956.4057378098369	936.3629340786465	500000	0.99601593625498	0.09901475429766744
177.2096471786499	300	1293.5877593839405	9.478353488008237	1318.673890946433	1269.3902126434841	600000	0.9966777408637871	0.09901475429766744
204.7934787273407	350	1562.8700169526887	11.364296880330356	1587.8852833881974	1532.5327741778456	700000	0.997150997150997	0.09901475429766744
232.71366810798645	400	1706.4681947186834	17.70876486514767	1755.1348552098498	1664.1171367187053	800000	0.9975062344139649	0.09901475429766744
261.9441456794739	450	1589.780866045059	11.906527690821832	1626.2332341894507	1561.5956333409995	900000	0.9977827050997782	0.09901475429766744
292.43551802635193	500	1726.6580573207134	17.17248888170336	1777.7998808226548	1687.0396724212915	1000000	0.9980039920159679	0.09901475429766744
298.1639337539673	501	1752.5991280878497	15.893854943856153	1808.612222276628	1722.8530144236283	1002000	0.9980079681274899	0.09901475429766744
