ResearchBenchmarksReinforcement Learning on OpenAI Gym Walker v1Reinforcement Learning on OpenAI Gym Walker v1Follow5,867Mean RewardRBF5,208.685,379.595,550.55,721.41Mar 8, 2017Evaluation resultsMethodMethodLinksMean RewardStochastic RewardRBFPolicy Architecture=RBFPolicy Architecture=RBF2017.035,8675,631NNPolicy Architecture=Ne...Policy Architecture=Neural Network, Training Algorithm=TRPO2017.035,594—LinearPolicy Architecture=Li...Policy Architecture=Linear2017.035,2344,881