Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
9.402057886123657	0	-2.034883604204183	19.01462660909523	29.63334692362696	-28.492423448711634	0	0.0	0
52.501901388168335	10	132.64646670397119	5.119550251614736	143.9660363826988	119.37909135203154	1000000	2.701077859946631	1.8572989474202437
95.50382995605469	20	245.63026507465503	12.533776095102226	260.54416441186913	220.23932120308746	2000000	2.811694020766583	2.0334832561768157
138.7746937274933	30	254.2318728311467	8.318755777769262	271.57669902499765	237.5277532666223	3000000	2.8200141646326604	2.541125399715441
183.95154738426208	40	256.4997403896891	3.1232407388200674	262.30233392864466	243.10798018123023	4000000	2.8556496382043406	2.6353024862375247
228.12677812576294	50	265.10573053523353	2.1093772507816606	269.884708528989	260.5615669085382	5000000	2.8643927764398107	2.6353024862375247
272.6550667285919	60	263.34012837059936	4.769231090644248	270.2518669652054	251.747996407561	6000000	2.8875891514389824	2.6353024862375247
315.94366335868835	70	262.44514374318237	2.0525119234607687	266.972906558236	257.238540793187	7000000	2.904357937900328	2.6353024862375247
360.34368801116943	80	264.5027859334468	3.522968631661145	273.7135465013853	256.41660592410335	8000000	2.9744217888217497	2.6353024862375247
405.0996870994568	90	255.14878320105046	5.3034289347353205	265.8681657612906	245.29053521656897	9000000	3.025659407485805	3.1087564649100607
450.0123550891876	100	269.73128596172	1.2636246929866286	272.5264809955261	267.2342520901002	10000000	3.04156038348018	3.1087564649100607
