{"id":"W1526144783","doi":"10.1007/11564096_59","title":"Active Learning in Partially Observable Markov Decision Processes","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Markov decision process; Observable; Computer science; Process (computing); Markov process; Mathematical optimization; Decision problem; Artificial intelligence; Decision process; Markov chain; Markov model; Machine learning; Mathematics; Algorithm; Engineering; Management science; Statistics","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":[0.002593889,0.0009912386,0.00135056,0.0006403939,0.0006429615,0.001772182,0.001546568,0.001736069,0.002260913],"category_scores_gemma":[0.007850461,0.0008999797,0.0008629856,0.001083223,0.002185617,0.002603168,0.001704364,0.002739765,0.0003081673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001527847,"about_ca_system_score_gemma":0.001171755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003932287,"about_ca_topic_score_gemma":0.003079704,"domain_scores_codex":[0.9986945,0.0006810311,0.00005412363,0.0002182841,0.0002430321,0.0001090497],"domain_scores_gemma":[0.9926869,0.006604554,0.0002573535,0.0001427044,0.0001766175,0.0001319766],"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":[0.0001132173,0.00007334983,0.0005651047,0.0002024165,0.00006461769,0.0001278008,0.0001935875,0.7504304,0.0005468628,0.2079193,0.001298659,0.0384647],"study_design_scores_gemma":[0.00002210705,0.00001889343,0.00004608016,0.00001438864,0.000007600721,0.00001049807,0.0000105425,0.8820075,0.0001765746,0.116915,0.0007650074,0.000005754785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01240617,0.002290606,0.9794745,0.0005984801,0.00008777907,0.00003779648,0.00006067392,0.0002231508,0.004820708],"genre_scores_gemma":[0.7597335,0.003759789,0.2271774,0.0002448112,0.0003879645,0.0003452964,0.0002691055,0.0001094291,0.00797262],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003932287,"threshold_uncertainty_score":0.01371795,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0136294422937688,"score_gpt":0.2560121948938667,"score_spread":0.2423827526000979,"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."}}