ResearchBenchmarksRobust Reinforcement Learning on HalfCheetah fixed exponential adversary MuJoCoFollow8,256Avg PerformanceTC-M2TD3-421.761,831.124,0846,336.88Jun 12, 2024Evaluation ResultsMethodMethodLinksAvg PerformanceTC-M2TD3Oracle=trueOracle=true2024.068,256TC-RARLOracle=trueOracle=true2024.068,000TC-M2TD32024.067,139TC-M2TD3Stacked=trueStacked=true2024.067,041TC-RARLStacked=trueStacked=true2024.065,741DR2024.065,691TC-RARL2024.065,326M2TD32024.063,909M2TD3Oracle=trueOracle=true2024.063,780TD32024.062,302RARL2024.06228RARLOracle=trueOracle=true2024.06-88