ResearchBenchmarksReinforcement Learning on Walker-Gravity Back OpenAI Gym Mujoco (test)Reinforcement Learning on Walker-Gravity Back OpenAI Gym Mujoco (test)Follow364.18Average RewardVBLRL160.5584213.4217266.285319.1483Oct 20, 2022Evaluation resultsMethodMethodLinksAverage RewardVBLRLsamples per iteration=1xsamples per iteration=1x2022.10364.18T-HiP-MDPsamples per iteration=1xsamples per iteration=1x2022.10266.97EWCsamples per iteration=2xsamples per iteration=2x2022.10216.09LPG-FTWsamples per iteration=2xsamples per iteration=2x2022.10168.39