ResearchDatasetsCleanupCleanupFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-agent policy synthesisCleanup2.75U Score9Multi-agent Social Dilemma Equality EvaluationCleanup95.9Equality Score (E)9Social Outcome EvaluationCleanup Normal (train test)0.6Outcome U4Social Outcome EvaluationCleanup Hard (train test)31Outcome U4Robot Plan ExecutionCleanup real-world3Success Rate (New Objects)2