ResearchDatasetsTaxi environmentFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsVulnerable Agent IdentificationTaxi environment 100 agents, 50 adversaries938.78Performance28Vulnerable Agent IdentificationTaxi environment 50 agents, 25 adversaries508.67Performance28Reinforcement LearningTaxi environment stochastic-57Episode Return6