ResearchDatasetsPPO RunsFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsEarly screening of successful training runsPPO Runs CartPole, LunarLander, MiniGrid (10% of train)82Precision55
Early screening of successful training runsPPO Runs CartPole, LunarLander, MiniGrid (10% of train)82Precision55