{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002377165,0.0003638296,0.0004148875,0.0006393096,0.0005506985,0.0004471181,0.002775007,0.0002524359,0.00001981711],"category_scores_gemma":[0.0004723442,0.0003065933,0.0001463849,0.0007870321,0.0003111484,0.0006357455,0.001549265,0.0008287177,0.00007163629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007327083,"about_ca_system_score_gemma":0.0003864645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000139646,"about_ca_topic_score_gemma":0.00006046316,"domain_scores_codex":[0.9960647,0.00007763656,0.0007412867,0.0008882618,0.001541364,0.0006867282],"domain_scores_gemma":[0.9968283,0.0009694513,0.0008196232,0.0009034905,0.0003929871,0.00008612705],"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":[0.000003087538,0.00001667702,0.0006984904,0.00002733032,0.00002034153,0.00005376067,0.003567008,0.7786071,0.0007436774,0.02494418,0.000009256164,0.1913091],"study_design_scores_gemma":[0.00007142195,0.000117128,0.0002159552,0.0003767684,0.00001979547,0.00001036143,0.000005220057,0.9704525,0.007383419,0.0206509,0.0003034546,0.0003930068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002459783,0.00006168049,0.9938003,0.0002009907,0.001621726,0.0005156033,0.000001445167,0.0001419197,0.001196511],"genre_scores_gemma":[0.8604144,0.0001073865,0.1352899,0.0006288311,0.000579974,0.00006459368,0.00001074601,0.00009152498,0.002812563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8585104,"threshold_uncertainty_score":0.9999386,"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."}}