ResearchBenchmarksSafe Reinforcement Learning on obstacle Static dynamicsSafe Reinforcement Learning on obstacle Static dynamicsFollow0Mean Shield Invocations per EpisodeDMPS-0.160.9223.08May 22, 2024Evaluation resultsMethodMethodLinksMean Shield Invocations per EpisodeStd Dev Shield Invocations per EpisodeMean Safety Violations per EpisodeStd Dev Safety Violations per EpisodeDMPS2024.0500——MPS2024.0500——REVEL2024.0548——CPO2024.05——00PPO-lag2024.05——00TD32024.05——00