Time	Iteration	AverageReward	StdRewards	MaxRewardRollout	MinRewardRollout	timesteps	gradnorms	maxnorms
8.741055965423584	0	-1.4489036436221607	18.17712229330612	27.28727449197322	-27.71342122834176	0	0.0	0
39.106422424316406	50	74.67745397864346	2.9507475059782764	79.82377081748564	69.12758556962945	100000	8.136891099643073	6.88414960492412
69.70875906944275	100	82.71294705069312	7.253919378009614	95.0266919293208	45.865596528863534	200000	8.016408221695082	7.156567048617384
99.37341713905334	150	103.94565206978153	3.172733080253967	113.99617461953312	98.32190868585167	300000	7.9470488165577535	7.156567048617384
132.12587189674377	200	123.38474498237905	3.214446395387808	138.80690213409252	117.70234424853697	400000	8.027269242576464	7.156567048617384
162.23173213005066	250	198.34350105629372	9.687681913155453	210.31764718453633	146.31587386142928	500000	8.039354559592175	7.156567048617384
191.85253858566284	300	234.08435587028166	3.4264455879913847	243.00318167256773	224.39844900579192	600000	8.009141322508443	7.156567048617384
220.31366872787476	350	237.41293183704002	1.8818822745340666	241.20937724006944	232.20956344436854	700000	7.970251946737753	7.156567048617384
248.53513860702515	400	340.3500277548348	2.251747421807048	344.6864068171126	333.14140842005145	800000	7.979292662623791	7.156567048617384
276.7528281211853	450	352.1072620573892	2.451543451330686	356.91989092028234	344.6126665393822	900000	7.997499275858569	7.156567048617384
305.3658232688904	500	353.49587534705347	2.7580379233593826	359.2490613921691	344.6536919577047	1000000	7.983113504433292	7.176210975120038
308.9221398830414	501	352.2003202743235	2.8811929881197478	357.4534179860493	343.5345705613727	1002000	7.985504192200527	7.176210975120038
