{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001163544,0.0005660891,0.0005987408,0.0009079109,0.0003063457,0.0006652409,0.003152302,0.000332385,0.00004716178],"category_scores_gemma":[0.0006070851,0.0005143266,0.00009648552,0.001222458,0.0002991029,0.0009858296,0.001369075,0.001889099,0.00006840955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003289825,"about_ca_system_score_gemma":0.001110074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006381712,"about_ca_topic_score_gemma":0.0006511511,"domain_scores_codex":[0.9955652,0.00007106752,0.0005853737,0.001782924,0.001143677,0.0008517799],"domain_scores_gemma":[0.9972443,0.001092363,0.0003327482,0.0008822086,0.0002704364,0.0001779209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009928291,0.00002517902,0.0003148177,0.00002913683,0.000003402778,0.00007616907,0.000620189,0.2155242,0.0000133175,0.0006004876,0.000007258394,0.7827759],"study_design_scores_gemma":[0.0004685749,0.0002443921,0.001229261,0.001057974,0.000004885896,0.00005993928,4.095691e-7,0.9502536,0.0005294633,0.03459003,0.01070389,0.0008575473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004691335,0.0005527925,0.9927317,0.0008627181,0.0008734385,0.0002897067,0.000001441054,0.0002426221,0.003976429],"genre_scores_gemma":[0.1430684,0.0002325129,0.8518764,0.001258884,0.001030211,0.00002213562,0.000008278728,0.00006977779,0.002433432],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7819184,"threshold_uncertainty_score":0.9997308,"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."}}