ResearchTasksMultimodal Policy Fine-TuningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGaussian-mixture environment G2DPPO100SR7May 13, 2026Gaussian-mixture environment (G1 landscape)DSRL100Success Rate (SR)7May 13, 2026