{"id":"W4404351472","doi":"10.1145/3677052.3698668","title":"EX-DRL: Hedging Against Heavy Losses with EXtreme Distributional Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Environmental science; Artificial intelligence; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002936458,0.0008305355,0.001154937,0.0004511341,0.0002593614,0.001044809,0.001607767,0.001084403,0.003331301],"category_scores_gemma":[0.007760037,0.0004134933,0.0005215895,0.0003909727,0.0008749631,0.001306976,0.001751851,0.001880377,0.0005589369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006383482,"about_ca_system_score_gemma":0.001019862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002433914,"about_ca_topic_score_gemma":0.002544339,"domain_scores_codex":[0.9990583,0.0003970537,0.00005420912,0.0001831869,0.0002089357,0.00009834425],"domain_scores_gemma":[0.9966369,0.002025963,0.0003339214,0.0003307892,0.0004841816,0.0001882298],"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":[0.0001533112,0.0001494352,0.002442368,0.00008164359,0.00006402316,0.0001124645,0.00006289919,0.9041458,0.001090659,0.007589095,0.001647193,0.08246101],"study_design_scores_gemma":[0.00001164213,0.000031357,0.0000904487,0.000005144244,0.000004217974,0.00001118549,0.000003160732,0.9966453,0.0001961802,0.002791137,0.0002058782,0.000004364186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03946935,0.0004473452,0.9554024,0.0004525361,0.00006159053,0.0000852313,0.0001069464,0.001197467,0.00277722],"genre_scores_gemma":[0.8730457,0.0002404834,0.1226538,0.0005024658,0.00005776899,0.0001539051,0.0002194616,0.0001211983,0.003005184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003331301,"threshold_uncertainty_score":0.01552963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07769634120264451,"score_gpt":0.3399878389204604,"score_spread":0.2622914977178159,"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."}}