ResearchBenchmarksReinforcement Learning on ST-obstacleFollow32.9Mean Performance ScoreTD3-44.58-24.465-4.3515.765May 22, 2024Evaluation ResultsMethodMethodLinksMean Performance ScoreStd Dev PerformanceTD32024.0532.90CPO2024.0532.80PPO-Lag2024.0532.80.4DMPS2024.0532.70.3MPS2024.058.647.9REVEL2024.05-41.652.7