{"id":"W4387918213","doi":"10.1007/978-3-031-44505-7_8","title":"Explaining the Behavior of Reinforcement Learning Agents Using Association Rules","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Association rule learning; Lift (data mining); Artificial intelligence; Learning classifier system; Process (computing); Machine learning; Association (psychology); Reinforcement","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":[0.000465057,0.0005682514,0.0004088983,0.0003250885,0.0002810101,0.0008785981,0.001102797,0.0009780113,0.004624336],"category_scores_gemma":[0.002315309,0.0003842727,0.0007489513,0.0003805528,0.0006253672,0.001088514,0.0006066317,0.001260766,0.0005822934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004534424,"about_ca_system_score_gemma":0.0005181126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005207293,"about_ca_topic_score_gemma":0.004524373,"domain_scores_codex":[0.9998079,0.00008727691,0.00001341282,0.00003010129,0.00003837587,0.000022929],"domain_scores_gemma":[0.9988683,0.0008967901,0.00006974919,0.00007653944,0.00005919921,0.00002941255],"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":[0.00004400935,0.00005097166,0.001131794,0.00007490699,0.00005499569,0.0002103268,0.000160912,0.823567,0.001790743,0.1404552,0.001496677,0.03096242],"study_design_scores_gemma":[0.00001222435,0.000009631002,0.0001210196,0.00001024573,0.00001040511,0.00002614073,0.00001095738,0.9395784,0.0004533909,0.05858464,0.001176829,0.000006183269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04967568,0.0005917323,0.9345376,0.001024404,0.0001158747,0.00005517859,0.0001165082,0.0009057723,0.01297726],"genre_scores_gemma":[0.7351566,0.0009584742,0.2524867,0.0001418156,0.00006592822,0.0001205674,0.0002142679,0.0001536393,0.01070203],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005207293,"threshold_uncertainty_score":0.01546997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06139241282526747,"score_gpt":0.3017173438229634,"score_spread":0.2403249309976959,"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."}}