ResearchBenchmarksReinforcement Learning on OpenAI Gym Cheetah v1Reinforcement Learning on OpenAI Gym Cheetah v1Follow6,620Mean RewardRBF4,050.164,717.335,384.56,051.67Mar 8, 2017Evaluation resultsMethodMethodLinksMean RewardStochastic RewardRBFPolicy Architecture=RBFPolicy Architecture=RBF2017.036,6206,477NNPolicy Architecture=Ne...Policy Architecture=Neural Network, Training Algorithm=TRPO2017.034,800—LinearPolicy Architecture=Li...Policy Architecture=Linear2017.034,1493,810