ResearchBenchmarksReinforcement Learning on Cheetah-Bodyparts Back OpenAI Gym Mujoco (test)Reinforcement Learning on Cheetah-Bodyparts Back OpenAI Gym Mujoco (test)Follow181.6Average RewardVBLRL-14,452.1464-10,653.0007-6,853.855-3,054.7093Oct 20, 2022Evaluation resultsMethodMethodLinksAverage RewardVBLRLsamples per iteration=1xsamples per iteration=1x2022.10181.6T-HiP-MDPsamples per iteration=1xsamples per iteration=1x2022.10116.03LPG-FTWsamples per iteration=2xsamples per iteration=2x2022.10-116.41EWCsamples per iteration=2xsamples per iteration=2x2022.10-13,889.31