| {"trainmethod": "RND", "envid": "MontezumaRevengeNoFrameskip-v4", "maxstepperepisode": 4500, "learningrate": 0.0001, "numenv": 1, "numstep": 128, "gamma": 0.999, "intgamma": 0.99, "lambda": 0.95, "usegae": true, "clipgradnorm": 0.5, "entropy": 0.001, "epoch": 4, "minibatch": 4, "ppoeps": 0.1, "extcoef": 2.0, "intcoef": 1.0, "stickyaction": false, "actionprob": 0.25, "lifedone": false, "obsnormstep": 50} |