Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
11.62639307975769	0	-0.3256862120560914	0.6918461223251973	1.1818802288416035	-2.4994383594774403	0	0.0	0
39.33216166496277	50	839.3677944789338	21.800765216621034	874.906607110468	693.8041131185018	100000	19.664550254806066	7.2809213982718495
66.21997165679932	100	916.8970531473742	350.7709505807892	1125.1917517162947	-19.53893911204068	200000	19.91154117547852	7.2809213982718495
92.559317111969	150	1238.8506518758293	655.819906296374	1811.8693587081507	-909.0399658894166	300000	20.036334748640964	7.460145164858131
119.29081201553345	200	1157.963128694394	403.7578379330069	1526.2150606154464	-20.860868138377555	400000	20.098869435493892	8.829890616144073
145.82724332809448	250	2051.7050718217088	321.7810742415613	2334.0949354935437	-474.09646091330796	500000	20.1773823244453	8.829890616144073
172.26301527023315	300	2559.2333240632556	84.56853387341812	2699.8354299364146	2273.165691483766	600000	20.20021370975892	8.829890616144073
200.42102670669556	350	2015.5642268402794	238.65431850663745	2327.3020172789693	1164.3306146369432	700000	20.211663812808705	8.829890616144073
227.39157485961914	400	2471.9833971634857	394.22784636738265	2693.603144707158	-197.3019458130002	800000	20.22213894152624	8.829890616144073
254.3971631526947	450	2533.5928530639976	609.7648981375086	3008.745671014767	-356.4104593489901	900000	20.226280524322984	8.829890616144073
282.150842666626	500	2571.0451989962876	441.0494391677771	2812.1307309763506	-160.0492737868335	1000000	20.229416989690332	8.829890616144073
285.28131222724915	501	2502.040859880755	432.46002539742034	2776.957211466506	184.7531790810608	1002000	20.23048092870614	8.829890616144073
