ResearchBenchmarksReinforcement Learning on OpenAI Gym Hopper v1Reinforcement Learning on OpenAI Gym Hopper v1Follow3,810Mean RewardRBF3,644.643,687.573,730.53,773.43Mar 8, 2017Evaluation resultsMethodMethodLinksMean RewardStochastic RewardRBFPolicy Architecture=RBFPolicy Architecture=RBF2017.033,8103,590NNPolicy Architecture=Ne...Policy Architecture=Neural Network, Training Algorithm=TRPO2017.033,668—LinearPolicy Architecture=Li...Policy Architecture=Linear2017.033,6513,466