ResearchBenchmarksNavigation on VMASFollow2.93Mean Episodic RewardIPPO0.66281.25141.842.4286Aug 12, 2024Evaluation ResultsMethodMethodLinksMean Episodic RewardIPPOEnvironment Steps=2×10^5Environment Steps=2×10^52024.082.93CoHetteamEnvironment Steps=2×10^5Environment Steps=2×10^52024.081.97CoHetselfEnvironment Steps=2×10^5Environment Steps=2×10^52024.081.8HetGPPOEnvironment Steps=2×10^5Environment Steps=2×10^52024.080.75