ResearchBenchmarksReinforcement Learning on OpenAI Gym Humanoid v1Reinforcement Learning on OpenAI Gym Humanoid v1Follow6,849Mean RewardRBF6,423.646,534.076,644.56,754.93Mar 8, 2017Evaluation resultsMethodMethodLinksMean RewardStochastic RewardRBFPolicy Architecture=RBFPolicy Architecture=RBF2017.036,8496,237NNPolicy Architecture=Ne...Policy Architecture=Neural Network, Training Algorithm=TRPO2017.036,482—LinearPolicy Architecture=Li...Policy Architecture=Linear2017.036,4405,873