ResearchBenchmarksReverse Transport on VMASFollow7.92Mean Episodic RewardIPPO0.68162.56084.446.3192Aug 12, 2024Evaluation ResultsMethodMethodLinksMean Episodic RewardIPPOEnvironment Steps=2×10^5Environment Steps=2×10^52024.087.92CoHetteamEnvironment Steps=2×10^5Environment Steps=2×10^52024.085.27CoHetselfEnvironment Steps=2×10^5Environment Steps=2×10^52024.085.13HetGPPOEnvironment Steps=2×10^5Environment Steps=2×10^52024.080.96