episodes,rewards,steps 0,-832.4413162158323,200 1,-968.4036079738249,200 2,-874.5862306381961,200 3,-875.7265412473744,200 4,-897.6813364592543,200 5,-1568.3188263407867,200 6,-1459.1205728839695,200 7,-1240.3308986778293,200 8,-1134.8423085380664,200 9,-5.36664590710244,200 10,-650.5003287883866,200 11,-8.377575660447649,200 12,-4.5756982919706335,200 13,-3.627742564378688,200 14,-3.893889252491577,200 15,-3.8192645919291257,200 16,-3.4146845438017186,200 17,-2.7635981143628925,200 18,-2.4017956104121017,200 19,-3.090478935757363,200 20,-1.4809018908948575,200 21,-1.2630981739795628,200 22,-1.3180949949636327,200 23,-1.564526506341134,200 24,-1.5223962556642976,200 25,-1.707998195828492,200 26,-1.4226643582643066,200 27,-1.5365465560984268,200 28,-1.5239148208423863,200 29,-1.4588095000150678,200 30,-1.7359744252202507,200 31,-2.0682890284663578,200 32,-1.741025565051244,200 33,-1.8488817690283263,200 34,-1.39893985171838,200 35,-1.4707914551719694,200 36,-1.4797493231032233,200 37,-1.4525725387039807,200 38,-1.4103713564691112,200 39,-1.3618191088451532,200 40,-1.322506170922359,200 41,-1.3324320670299856,200 42,-1.4468348751323956,200 43,-1.3540026843790918,200 44,-1.3097180192945221,200 45,-1.4315286227920205,200 46,-1.4223011898198696,200 47,-1.3803119102174926,200 48,-1.383840087083155,200 49,-1.285964624772213,200 50,-1.2869926211551335,200 51,-1.3431550684354865,200 52,-1.3886544335397744,200 53,-1.4759717484102066,200 54,-1.626338794891603,200 55,-1.644649473947096,200 56,-1.6638041634800558,200 57,-1.7398234937547132,200 58,-1.680024377278263,200 59,-1.7947581457511599,200 60,-1.7891190829763475,200 61,-1.7632050654476048,200 62,-1.8211882825454626,200 63,-1.8442752105447826,200 64,-1.9176680463940405,200 65,-1.8047871753057574,200 66,-1.7846120425902607,200 67,-1.8608097138458495,200 68,-1.8351909400796054,200 69,-1.8555094919167812,200 70,-1.9327542950993424,200 71,-1.9822565698772594,200 72,-1.8954672018586112,200 73,-1.9557719773884903,200 74,-1.8844351899739862,200 75,-1.883524519131489,200 76,-1.8207078088705415,200 77,-1.8741586443072578,200 78,-1.897463137234909,200 79,-1.5191278207011145,200 80,-0.9455138132785595,200 81,-0.8036250047483352,200 82,-1.2124938658523443,200 83,-1.3321687125553676,200 84,-1.605031143258114,200 85,-1.488155427061823,200 86,-1.5151577723764103,200 87,-1.5704170742235621,200 88,-1.6685888937499647,200 89,-1.6493756229468635,200 90,-1.5729133065433396,200 91,-1.5856557451539273,200 92,-1.6196725146806101,200 93,-1.7767693701781986,200 94,-1.8225698294766743,200 95,-1.7551168262928307,200 96,-1.7761588517008813,200 97,-1.7324583634362947,200 98,-1.7706494685091234,200 99,-1.7833268395875401,200