Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
14.96788501739502	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
75.77235078811646	10	146.65045313005666	4.997973126704214	156.97873593900295	135.72132369314204	1000000	1.2306355059158636	0.5
133.57681107521057	20	329.04250539557574	2.5752578113980813	334.98340571738663	323.3080443831859	2000000	1.3595051634375157	0.5
192.37409472465515	30	353.7831430082816	3.0528147793584193	358.9080920901615	346.18743016725057	3000000	1.3609954318044877	0.5
251.07069444656372	40	353.8992212910039	2.1756008508506874	358.3496090557601	346.6069813533686	4000000	1.3111446459004281	0.5
306.2127342224121	50	356.5239676674748	2.854429419252146	361.1776181422174	346.8349377461709	5000000	1.2748878060677546	0.5
362.19887375831604	60	355.5521134396128	2.67088929209446	359.8908644124167	348.9465481082734	6000000	1.2616478802617777	0.5
420.40814089775085	70	354.3586347921197	1.9513762127311691	359.2772203228087	349.40907496219734	7000000	1.2490682816473717	0.5
478.22739362716675	80	354.87346422929454	2.0295313482929513	360.48791442171205	350.17997957230546	8000000	1.226242720852224	0.5
534.2379591464996	90	354.59752114269855	2.24046141882224	358.77622179401806	348.8341989889741	9000000	1.2167146487260831	0.5
588.5320432186127	100	354.44306987286996	2.023989776301498	358.25930144940503	349.00977472998784	10000000	1.213090540674953	0.5
