Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
15.162983417510986	0	0.10479357355305183	19.050881585284408	28.75317772757262	-27.52097297552973	0	0.0	0
83.93418169021606	10	247.7920007386306	3.473948213263538	255.89730277490162	238.85828182497062	1000000	1.8676510299123656	1.370060069359942
151.6068298816681	20	339.11566494179147	2.766360437327461	345.9029111974487	333.4116735201096	2000000	2.0721377121323834	1.418044369213995
219.82009553909302	30	350.6736490367697	2.6340386374509115	355.59459872497246	344.00407024502056	3000000	1.9792756210442692	1.4246333307796275
287.4122271537781	40	353.54563568455495	2.3526176249124378	358.6084132095566	348.0296590803191	4000000	1.845340845151817	1.4246333307796275
354.8450622558594	50	352.9358060635761	2.3934885150555947	357.8076821286231	347.4397129440331	5000000	1.7434221824558571	1.4246333307796275
421.8311183452606	60	354.93787147762936	2.1789341406080647	359.6785915073742	347.07294440310216	6000000	1.660152396046045	1.4246333307796275
488.9460699558258	70	353.6640274699661	2.3600410764651962	358.7826061755186	348.6441543569381	7000000	1.6171477929599696	1.4246333307796275
555.5596539974213	80	353.92176583026844	1.9970798185646306	358.94047625240637	349.85472451581154	8000000	1.5684912700907312	1.4246333307796275
622.7294456958771	90	354.9325706293224	2.209654591839644	360.1391400891589	350.4371019907412	9000000	1.5307551208642058	1.4246333307796275
689.7332813739777	100	354.3103470194056	2.3406160211257467	360.597126408451	347.0848191055702	10000000	1.5225380881021848	1.4246333307796275
