{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001822599,0.001692746,0.001766019,0.0008094936,0.0009390407,0.001468614,0.001948461,0.001534261,0.007722979],"category_scores_gemma":[0.00600829,0.0008495533,0.001174635,0.0009942529,0.00140311,0.002278903,0.00210889,0.002522729,0.0008390297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001661369,"about_ca_system_score_gemma":0.002689934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006411201,"about_ca_topic_score_gemma":0.007155139,"domain_scores_codex":[0.9988386,0.0004038612,0.00008412098,0.0002477339,0.0002826798,0.0001430957],"domain_scores_gemma":[0.9959903,0.003198366,0.0002709852,0.0002339043,0.0001839165,0.0001224953],"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":[0.00007728505,0.00007793029,0.0002494052,0.0001798804,0.000042349,0.00005522608,0.00006714846,0.9046542,0.0003635836,0.04603207,0.001524885,0.04667607],"study_design_scores_gemma":[0.00003477538,0.00002201183,0.0000274054,0.00001714049,0.000009255294,0.00001306346,0.00001434918,0.9623732,0.0002269494,0.0362148,0.001041439,0.000005562395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004665816,0.0005017859,0.9902807,0.0001623839,0.00004451199,0.00008982225,0.0000942896,0.0007344637,0.003426085],"genre_scores_gemma":[0.381019,0.001102506,0.6122476,0.0002131879,0.00009034325,0.0007896485,0.0005325382,0.000298679,0.003706469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007722979,"threshold_uncertainty_score":0.02583593,"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."}}