ResearchBenchmarksRobust Reinforcement Learning on Walker fixed exponential adversary MuJoCoRobust Reinforcement Learning on Walker fixed exponential adversary MuJoCoFollow5,310Average PerformanceTC-M2TD31,463.042,461.773,460.54,459.23Jun 12, 2024Evaluation resultsMethodMethodLinksAverage PerformanceTC-M2TD3Stacked=trueStacked=true2024.065,310TC-M2TD3Oracle=trueOracle=true2024.065,161TC-M2TD32024.064,910M2TD3Oracle=trueOracle=true2024.064,767TC-RARLOracle=trueOracle=true2024.064,650TC-RARLStacked=trueStacked=true2024.064,376M2TD32024.064,274DR2024.064,224TC-RARL2024.064,017TD32024.062,768RARL2024.062,053RARLOracle=trueOracle=true2024.061,611