{"transitions":[[{"__dict__":[["Q",{"__nd__":[[0.30471707975443135,-1.0399841062404955],[0.7504511958064572,0.9405647163912139],[-1.9510351886538364,-1.302179506862318],[0.12784040316728537,-0.3162425923435822]],"dtype":"float64","shape":[4,2]}],["alpha",0.1],["gamma",0.99],["steps",[{"__dict__":[["s",2],["a",0],["r",-0.85304392757358],["s_next",2],["a_next",0],["done",false]]},{"__dict__":[["s",3],["a",1],["r",1.1272412069680329],["s_next",2],["a_next",0],["done",true]]},{"__dict__":[["s",0],["a",1],["r",-0.9588826008289989],["s_next",3],["a_next",1],["done",false]]},{"__dict__":[["s",0],["a",1],["r",-0.6809295444039414],["s_next",0],["a_next",1],["done",false]]},{"__dict__":[["s",2],["a",1],["r",-0.3521335504882296],["s_next",1],["a_next",0],["done",true]]},{"__dict__":[["s",2],["a",0],["r",0.43082100300788273],["s_next",3],["a_next",1],["done",false]]}]]]},{"__dict__":[["q",{"__nd__":[[0.30471707975443135,-0.9552219437519116],[0.7504511958064572,0.9405647163912139],[-1.7173983501383128,-1.2071749112249093],[0.12784040316728537,-0.17189421241242067]],"dtype":"float64","shape":[4,2]}],["sarsa",{"__nd__":[[0.30471707975443135,-1.1159355456858413],[0.7504511958064572,0.9405647163912139],[-1.8048851183283277,-1.2071749112249093],[0.12784040316728537,-0.17189421241242067]],"dtype":"float64","shape":[4,2]}]]}],[{"__dict__":[["Q",{"__nd__":[[-0.5122427290715373,-0.8137727282478777,0.6159794225754956],[1.1289722927208916,-0.11394745765487507,-0.840156476962528],[-0.8244812156912396,0.6505927878247011,0.7432541712034423],[0.543154268305195,-0.6655097072886943,0.23216132306671977],[0.11668580914072822,0.21868859672901295,0.8714287779481898],[0.22359554877468227,0.6789135630718949,0.06757906948889146]],"dtype":"float64","shape":[6,3]}],["alpha",0.5],["gamma",0.9],["steps",[{"__dict__":[["s",4],["a",2],["r",0.6312882258385404],["s_next",2],["a_next",2],["done",false]]},{"__dict__":[["s",3],["a",1],["r",-0.6388778482433419],["s_next",0],["a_next",0],["done",true]]},{"__dict__":[["s",2],["a",2],["r",0.9682783545914808],["s_next",5],["a_next",1],["done",false]]},{"__dict__":[["s",3],["a",1],["r",0.5862223313592781],["s_next",0],["a_next",1],["done",false]]},{"__dict__":[["s",3],["a",0],["r",-0.46235179266456716],["s_next",5],["a_next",0],["done",false]]},{"__dict__":[["s",5],["a",2],["r",-1.1332872140034806],["s_next",4],["a_next",0],["done",true]]}]]]},{"__dict__":[["q",{"__nd__":[[-0.5122427290715373,-0.8137727282478777,0.6159794225754956],[1.1289722927208916,-0.11394745765487507,-0.840156476962528],[-0.8244812156912396,0.6505927878247011,1.1612773662798144],[0.3459123412026666,0.24420501695560304,0.23216132306671977],[0.11668580914072822,0.21868859672901295,1.085822878934914],[0.22359554877468227,0.6789135630718949,-0.5328540722572945]],"dtype":"float64","shape":[6,3]}],["sarsa",{"__nd__":[[-0.5122427290715373,-0.8137727282478777,0.6159794225754956],[1.1289722927208916,-0.11394745765487507,-0.840156476962528],[-0.8244812156912396,0.6505927878247011,1.1612773662798144],[0.14101923476892092,-0.3991834509149149,0.23216132306671977],[0.11668580914072822,0.21868859672901295,1.085822878934914],[0.22359554877468227,0.6789135630718949,-0.5328540722572945]],"dtype":"float64","shape":[6,3]}]]}],[{"__dict__":[["Q",{"__nd__":[[0.14242573607056525,0.6904853540677682,-0.42725264633653426,0.15853969107671423],[0.6255903939673367,-0.3093465397202384,0.45677523755741145,-0.6619259410666513],[-0.3630538465650718,-0.3817378939983291,-1.1958396455890397,0.4869724807855818]],"dtype":"float64","shape":[3,4]}],["alpha",0.25],["gamma",0.5],["steps",[{"__dict__":[["s",2],["a",0],["r",0.01249411872768743],["s_next",2],["a_next",0],["done",false]]},{"__dict__":[["s",1],["a",1],["r",-0.09848548450942361],["s_next",0],["a_next",1],["done",false]]},{"__dict__":[["s",1],["a",1],["r",-1.4471124724230873],["s_next",1],["a_next",0],["done",false]]},{"__dict__":[["s",1],["a",3],["r",-0.9054790553600608],["s_next",1],["a_next",1],["done",false]]},{"__dict__":[["s",0],["a",3],["r",0.7375155684670865],["s_next",2],["a_next",1],["done",true]]},{"__dict__":[["s",0],["a",0],["r",-0.3390330759005625],["s_next",0],["a_next",1],["done",true]]}]]]},{"__dict__":[["q",{"__nd__":[[0.022061033077783315,0.6904853540677682,-0.42725264633653426,0.3032836604243073],[0.6255903939673367,-0.41131977385415247,0.45677523755741145,-0.6446154203940866],[-0.20829529514368425,-0.3817378939983291,-1.1958396455890397,0.4869724807855818]],"dtype":"float64","shape":[3,4]}],["sarsa",{"__nd__":[[0.022061033077783315,0.6904853540677682,-0.42725264633653426,0.3032836604243073],[0.6255903939673367,-0.41131977385415247,0.45677523755741145,-0.7742291913717727],[-0.31454858606251596,-0.3817378939983291,-1.1958396455890397,0.4869724807855818]],"dtype":"float64","shape":[3,4]}]]}]],"policies":[[{"__dict__":[["Q",{"__nd__":[[0.2,0.7,-0.6],[-0.9,-2.0,-0.9]],"dtype":"float64","shape":[2,3]}],["epsilon",0.2],["seed",100]]},[1,0,1,1,1,0,1,0,2,0,1,0,1,0,1,0,1,0,1,0]],[{"__dict__":[["Q",{"__nd__":[[0.0,0.2,-0.8,1.2,0.9],[-0.1,-0.6,-0.4,-0.8,-0.1]],"dtype":"float64","shape":[2,5]}],["epsilon",0.6],["seed",101]]},[3,0,3,1,3,4,3,4,3,4,3,4,2,0,1,0,1,1,3,0]],[{"__dict__":[["Q",{"__nd__":[[-0.6,0.6],[-0.4,-0.4]],"dtype":"float64","shape":[2,2]}],["epsilon",0.05],["seed",102]]},[1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,0]]]}