ResearchBenchmarksReinforcement Learning on Hopper-Bodyparts Back OpenAI Gym Mujoco (test)Reinforcement Learning on Hopper-Bodyparts Back OpenAI Gym Mujoco (test)Follow316.74Average RewardVBLRL-412.3104-223.0377-33.765155.5077Oct 20, 2022Evaluation resultsMethodMethodLinksAverage RewardVBLRLsamples per iteration=1xsamples per iteration=1x2022.10316.74LPG-FTWsamples per iteration=2xsamples per iteration=2x2022.10285.62T-HiP-MDPsamples per iteration=1xsamples per iteration=1x2022.10211.95EWCsamples per iteration=2xsamples per iteration=2x2022.10-384.27