{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002217661,0.001548872,0.00155115,0.0005233198,0.0004617975,0.001174999,0.001944961,0.001510267,0.003493189],"category_scores_gemma":[0.008306174,0.0006629031,0.0007832551,0.0004363939,0.001563929,0.001190364,0.002160822,0.003170535,0.0009705062],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001183804,"about_ca_system_score_gemma":0.002388311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004519799,"about_ca_topic_score_gemma":0.00511109,"domain_scores_codex":[0.9987936,0.0004168921,0.00007021795,0.0002817394,0.0003115854,0.0001259224],"domain_scores_gemma":[0.997072,0.001825883,0.0002743039,0.0002678294,0.0003802099,0.0001797175],"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":[0.00007551834,0.0000384837,0.0004230888,0.00007282795,0.00004828825,0.00006088718,0.00004511351,0.9454688,0.001244517,0.01157815,0.001804297,0.03913993],"study_design_scores_gemma":[0.000006859689,0.00001177458,0.00001904617,0.000004785174,0.000002772427,0.000007359007,0.000001960054,0.9960713,0.0002547943,0.003396526,0.0002196982,0.000003082971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005574003,0.000189937,0.9908032,0.0001771165,0.00005822576,0.00004335459,0.00004155909,0.001223841,0.001888687],"genre_scores_gemma":[0.719243,0.0002813764,0.2730975,0.0005278289,0.0001087413,0.000287207,0.0003641022,0.0006125569,0.0054777],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004519799,"threshold_uncertainty_score":0.01172829,"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."}}