ResearchBenchmarksReinforcement Learning on MuJoCo Hopper (Clean Reward, Best Attack Reward)Follow3,290,150Clean RewardPPO201,086.881,003,055.191,805,023.52,606,991.81Jun 6, 2024Evaluation ResultsMethodMethodLinksClean RewardBest Attack RewardPPOSmoothing=false, Time-...Smoothing=false, Time-discounting=false2024.063,290,150820,430TDRT-PPOSmoothing=true, Time-d...Smoothing=true, Time-discounting=true2024.063,214,1631,345,787SA-PPOSmoothing=true, Time-d...Smoothing=true, Time-discounting=false2024.06319,8971,579,672