ResearchBenchmarksReinforcement Learning on OpenAI Gym Swimmer v1Reinforcement Learning on OpenAI Gym Swimmer v1Follow366Mean RewardLinear121.6185.05248.5311.95Mar 8, 2017Evaluation resultsMethodMethodLinksMean RewardStochastic RewardLinearPolicy Architecture=Li...Policy Architecture=Linear2017.03366362RBFPolicy Architecture=RBFPolicy Architecture=RBF2017.03365361NNPolicy Architecture=Ne...Policy Architecture=Neural Network, Training Algorithm=TRPO2017.03131—