ResearchBenchmarksReinforcement Learning on Hopper-Gravity Back OpenAI Gym Mujoco (test)Reinforcement Learning on Hopper-Gravity Back OpenAI Gym Mujoco (test)Follow360.94Average RewardVBLRL298.6648314.8324331347.1676Oct 20, 2022Evaluation resultsMethodMethodLinksAverage RewardVBLRLsamples per iteration=1xsamples per iteration=1x2022.10360.94LPG-FTWsamples per iteration=2xsamples per iteration=2x2022.10347.07T-HiP-MDPsamples per iteration=1xsamples per iteration=1x2022.10312.11EWCsamples per iteration=2xsamples per iteration=2x2022.10301.06