{"id":"W2484023105","doi":"10.4018/978-1-60960-165-2.ch007","title":"Automatically Generated Explanations for Markov Decision Processes","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"AI-based Problem Solving and Planning","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Task (project management); Markov decision process; Set (abstract data type); Template; Domain (mathematical analysis); Probabilistic logic; Selection (genetic algorithm); Markov process; Markov chain; Artificial intelligence; Machine learning; Programming language; Engineering; Mathematics; Systems 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":[0.001383608,0.00125585,0.0004381671,0.001068553,0.0004203796,0.001300876,0.001535436,0.00138365,0.01377183],"category_scores_gemma":[0.01105771,0.0005274797,0.001072804,0.0006705214,0.0006757633,0.001636105,0.001343796,0.001659404,0.001477685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001208357,"about_ca_system_score_gemma":0.001108834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001696472,"about_ca_topic_score_gemma":0.00405111,"domain_scores_codex":[0.9986283,0.0006324635,0.00009360366,0.0001762973,0.0004155779,0.00005386064],"domain_scores_gemma":[0.9917276,0.007235014,0.0002699438,0.0003965208,0.000311697,0.00005927485],"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":[0.0002276907,0.0001904915,0.002031595,0.001108505,0.00009994524,0.001096015,0.001390416,0.3948238,0.005835817,0.2043456,0.0227902,0.36606],"study_design_scores_gemma":[0.00007963199,0.00003757117,0.000243905,0.0001651649,0.00003106732,0.0001765975,0.00009386136,0.8696344,0.004057768,0.1029729,0.02248191,0.00002520497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01301675,0.0003969572,0.9746644,0.0006407237,0.00006478808,0.0002296275,0.001124244,0.004370398,0.005492065],"genre_scores_gemma":[0.1365881,0.0004714661,0.8556712,0.0001538201,0.0000425341,0.0004441651,0.002335692,0.0004704629,0.003822623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01377183,"threshold_uncertainty_score":0.04607135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03116317868721368,"score_gpt":0.2570897931324819,"score_spread":0.2259266144452682,"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."}}