ResearchBenchmarksReinforcement Learning on Sparse MuJoCo Hopper v2 (test)Reinforcement Learning on Sparse MuJoCo Hopper v2 (test)Follow902.5Max Average ReturnMME813.996836.973859.95882.927Jun 19, 2021Evaluation resultsMethodMethodLinksMax Average ReturnMME2021.06902.5DAC2021.06900.3RND2021.06897.9DE-MME2021.06893.3MaxEnt(State)2021.06879.5SAC-Div2021.06817.4