{"id":"W1973749650","doi":"10.1016/j.artint.2012.04.006","title":"Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Task (project management); Artificial intelligence; Machine learning; Action (physics); Variety (cybernetics); Bayes' theorem; Bayesian probability; Markov chain; Markov process; Markov model; Mathematics","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":[0.001282506,0.0003881283,0.0003617155,0.0004226545,0.0006247291,0.0002793201,0.0007702283,0.0001450013,0.00004995654],"category_scores_gemma":[0.0007286512,0.0003687327,0.0001142639,0.001044237,0.0001011791,0.001700354,0.0003287406,0.0008035433,0.0000954072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000348397,"about_ca_system_score_gemma":0.0001370843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002330473,"about_ca_topic_score_gemma":0.00002381136,"domain_scores_codex":[0.9965747,0.0002139363,0.0008403509,0.0005583704,0.0006031219,0.001209536],"domain_scores_gemma":[0.997772,0.0006275699,0.0006263431,0.0005108825,0.0002428961,0.0002202446],"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":[0.0001093132,0.00004930527,0.005010305,0.0000251837,0.00005222577,0.000003151679,0.005890025,0.9379852,0.0004746804,0.02871855,0.000004299323,0.02167775],"study_design_scores_gemma":[0.000147603,0.0006545802,0.0003231009,0.0001086025,0.00003595111,0.000008079205,0.001278036,0.9719432,0.02290166,0.0004377677,0.001668146,0.0004932586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03559246,0.00005415967,0.961449,0.00008047197,0.000351202,0.0007710181,4.16968e-7,0.0003313165,0.001369968],"genre_scores_gemma":[0.9481544,0.00006331709,0.05106556,0.00009206697,0.0001708481,0.00007032926,0.00001340384,0.0000419812,0.0003280685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.912562,"threshold_uncertainty_score":0.9998764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06131471456678903,"score_gpt":0.3031917075469479,"score_spread":0.2418769929801589,"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."}}