{"id":"W4415112009","doi":"10.48550/arxiv.2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Electrical, Communications and Cyber Systems; Office of Naval Research; York University; National Science Foundation","keywords":"Robustness (evolution); Reinforcement learning; Robust control; Benchmark (surveying); Entropy (arrow of time); Convergence (economics); Robust optimization; Rate of convergence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005051677,0.0005487663,0.0005150766,0.000333328,0.0005830358,0.0003515344,0.002589165,0.0004454564,0.00005992965],"category_scores_gemma":[0.0003201723,0.0006640264,0.000451323,0.000617579,0.0001651356,0.000445094,0.002895377,0.001147817,0.00004697256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001165743,"about_ca_system_score_gemma":0.0009139068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008939379,"about_ca_topic_score_gemma":0.00001339831,"domain_scores_codex":[0.9969191,0.0001672817,0.0004749903,0.001384172,0.0002723843,0.0007820913],"domain_scores_gemma":[0.9967866,0.0006461344,0.0004542262,0.001285164,0.0006034286,0.0002244742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003008198,0.00002569226,0.0003078509,0.0001792853,0.0001571629,0.00001774165,0.00006149175,0.7525905,0.00000522775,0.2458071,0.0007155911,0.000102263],"study_design_scores_gemma":[0.0007724131,0.0001180584,0.0001590808,0.0002626689,0.0001383437,0.000001635419,0.00009074399,0.9830903,0.00002602911,0.008317726,0.006379215,0.0006437732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001198888,0.00003682864,0.9933951,0.0004945875,0.001067003,0.0007715888,0.00002828117,0.000474747,0.002532925],"genre_scores_gemma":[0.9581698,0.00009569475,0.003823376,0.0002812617,0.0001202014,0.000009762305,0.0004549765,0.00002438271,0.0370206],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9895718,"threshold_uncertainty_score":0.9995811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07787399934876577,"score_gpt":0.2187588312169848,"score_spread":0.1408848318682191,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}