{"id":"W4393157304","doi":"10.1609/aaai.v38i20.30606","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reprint; Reinforcement learning; Action (physics); Reinforcement; State action; Computer science; Cognitive psychology; Psychology; Artificial intelligence; Social psychology; Political science; Law; Physics","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":[0.00159289,0.0005889363,0.0007036898,0.0002864338,0.0003502933,0.0007493547,0.0008151993,0.0007049449,0.006072512],"category_scores_gemma":[0.008942412,0.0003453712,0.0003685837,0.0003924874,0.001402076,0.001426153,0.001379455,0.0023155,0.0007732685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006798785,"about_ca_system_score_gemma":0.001297413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003364386,"about_ca_topic_score_gemma":0.00337785,"domain_scores_codex":[0.9994967,0.000174137,0.00003004102,0.0001204104,0.0001154365,0.0000632592],"domain_scores_gemma":[0.9956648,0.0029141,0.0003223524,0.0006998408,0.0002206523,0.0001783023],"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":[0.0001869425,0.0001015458,0.001122469,0.00006399741,0.00002227824,0.0001027379,0.00006200623,0.8816798,0.00230508,0.03912905,0.002172824,0.07305124],"study_design_scores_gemma":[0.00001301712,0.00002916937,0.00009884185,0.000004938347,0.000002131859,0.0000126278,0.000003361201,0.9859229,0.0006486625,0.01273335,0.0005277365,0.000003163361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01613836,0.00008599878,0.9799086,0.000286079,0.00005151566,0.00004682429,0.00005609716,0.0005252748,0.002901247],"genre_scores_gemma":[0.8194185,0.0001415646,0.1757568,0.0002378474,0.0000666218,0.0001598418,0.0001586085,0.0001850362,0.00387502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006072512,"threshold_uncertainty_score":0.02031463,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1110147079960333,"score_gpt":0.3391604714125966,"score_spread":0.2281457634165632,"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."}}