ResearchBenchmarksReinforcement Learning on Cheetah-Gravity Back OpenAI Gym Mujoco (test)Reinforcement Learning on Cheetah-Gravity Back OpenAI Gym Mujoco (test)Follow231.79Average RewardVBLRL-6,948.4948-5,084.3824-3,220.27-1,356.1576Oct 20, 2022Evaluation resultsMethodMethodLinksAverage RewardVBLRLsamples per iteration=1xsamples per iteration=1x2022.10231.79T-HiP-MDPsamples per iteration=1xsamples per iteration=1x2022.1097.84LPG-FTWsamples per iteration=2xsamples per iteration=2x2022.10-29.95EWCsamples per iteration=2xsamples per iteration=2x2022.10-6,672.33