{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001346357,0.0002638092,0.0002643016,0.0001722132,0.0003455897,0.0008400404,0.000872215,0.00008838013,0.00003482269],"category_scores_gemma":[0.0008880345,0.0002036426,0.0001451889,0.0004452151,0.0001441395,0.000803502,0.0003997168,0.0004865078,0.00001825331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001308471,"about_ca_system_score_gemma":0.0001552403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007923522,"about_ca_topic_score_gemma":0.000002608558,"domain_scores_codex":[0.9977749,0.00001548553,0.0007009843,0.00059311,0.0004852246,0.0004302964],"domain_scores_gemma":[0.998433,0.0002703144,0.0004107225,0.0002705143,0.0005181191,0.00009733391],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001071958,0.00004430701,0.0001907569,0.0004320887,0.00008659933,0.000001473545,0.003086057,0.270412,0.09082403,0.4966014,0.00006841331,0.1381457],"study_design_scores_gemma":[0.00002650473,0.0003405552,0.0001714002,0.0004391291,0.0000177726,0.000009830414,0.0003261404,0.7677863,0.1938591,0.03661331,0.0002072447,0.0002027009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1281449,0.00004553529,0.8670768,0.0007711134,0.0004458654,0.0006760526,0.000002040647,0.000248677,0.002588969],"genre_scores_gemma":[0.9909164,0.0001219878,0.008133444,0.00003741659,0.00008267952,0.00003804196,0.000001737475,0.00002091528,0.000647362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8627715,"threshold_uncertainty_score":0.8304303,"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."}}