{"id":"W1507852408","doi":"10.48550/arxiv.1206.3281","title":"Model-Based Bayesian Reinforcement Learning in Large Structured Domains","year":2012,"lang":"en","type":"preprint","venue":"PubMed","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Institute of Mental Health","keywords":"Reinforcement learning; Computer science; Scalability; Artificial intelligence; Bayesian probability; Machine learning; Bayesian inference","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":[0.001623169,0.0005730608,0.0005860101,0.0005690299,0.0001739396,0.0004310849,0.002236874,0.000514642,0.0000242709],"category_scores_gemma":[0.0002324741,0.0005984779,0.0002254689,0.0004155869,0.00005274561,0.0004053464,0.002410503,0.002019771,0.00002044544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006714841,"about_ca_system_score_gemma":0.0002938815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002835335,"about_ca_topic_score_gemma":0.00002194267,"domain_scores_codex":[0.9953641,0.0002331277,0.000845381,0.0009033055,0.0009583247,0.001695714],"domain_scores_gemma":[0.9972104,0.0001005438,0.0006131907,0.001607378,0.00009704669,0.0003714248],"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":[0.00001092479,0.00002764932,0.005224332,0.0001236092,0.00003369991,0.00001048389,0.0004934805,0.9806731,0.000002560786,0.005361933,0.0001093738,0.007928846],"study_design_scores_gemma":[0.0008852113,0.00001225403,0.02047409,0.00005144823,0.00002141838,0.000001481846,0.00000965355,0.9756273,0.00007785191,0.0008088939,0.001417426,0.0006129417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001294617,0.0001160953,0.9886519,0.0004088978,0.001477917,0.00174112,0.000002600213,0.0004941691,0.005812643],"genre_scores_gemma":[0.9659882,0.00001703052,0.03007337,0.0004529135,0.0002031087,0.00155286,0.00009514784,0.00005658638,0.001560852],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9646935,"threshold_uncertainty_score":0.9996467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02538073376749116,"score_gpt":0.2424280285234937,"score_spread":0.2170472947560025,"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."}}