{"id":"W2144913588","doi":"10.1613/jair.2567","title":"Online Planning Algorithms for POMDPs","year":2008,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":515,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; McGill University","funders":"National Institute of Mental Health; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Partially observable Markov decision process; Computer science; Heuristic; Markov decision process; Mathematical optimization; Upper and lower bounds; Reduction (mathematics); Observable; Focus (optics); Computational complexity theory; Action (physics); Artificial intelligence; Machine learning; Markov process; Markov chain; Algorithm; Markov model; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.003161627,0.0001193069,0.0002483997,0.0006251191,0.0004626185,0.0001813799,0.001643503,0.00008752154,0.00001869915],"category_scores_gemma":[0.001290521,0.0001021837,0.0001577771,0.0008386896,0.0001733774,0.0006108243,0.0002307723,0.0008163073,0.00004755243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001424861,"about_ca_system_score_gemma":0.0005033809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008837411,"about_ca_topic_score_gemma":8.872053e-7,"domain_scores_codex":[0.9968257,0.000170885,0.000840912,0.0002181855,0.001341275,0.0006030769],"domain_scores_gemma":[0.9963918,0.001072907,0.0002897877,0.0003483959,0.001682321,0.0002148163],"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":[0.000167487,0.0007302961,0.0004819494,0.00005890309,0.0001337133,0.0006344534,0.008394283,0.7665037,0.003862735,0.0436602,0.004426053,0.1709463],"study_design_scores_gemma":[0.000070068,0.001535399,0.0001669656,0.00009343179,0.000004972575,0.0003390118,0.0007726636,0.9612532,0.01868797,0.00971067,0.007198069,0.0001675333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01414195,0.0001975009,0.9834687,0.001156918,0.0005757028,0.00019062,9.831576e-7,0.00003347589,0.0002341798],"genre_scores_gemma":[0.5305747,0.0002793267,0.4673403,0.00009028836,0.001237464,0.000006051502,0.000001624137,0.00002336433,0.0004469132],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5164327,"threshold_uncertainty_score":0.4166929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4539481331437369,"score_gpt":0.4870388551056944,"score_spread":0.0330907219619575,"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."}}