{"id":"W2122633037","doi":"10.1109/cdc.1989.70344","title":"Computationally efficient adaptive control algorithms for Markov chains","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; McGill University","funders":"","keywords":"Markov chain; A priori and a posteriori; Computer science; Computation; Optimal control; Markov decision process; Algorithm; Mathematical optimization; State (computer science); Markov process; Theoretical computer science; Mathematics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001700388,0.001262635,0.001286906,0.001014945,0.0008445724,0.001597034,0.001896853,0.001602556,0.006147014],"category_scores_gemma":[0.008551912,0.0007716675,0.0008046938,0.001109625,0.001533906,0.002086121,0.001946314,0.002882808,0.0009551902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00179479,"about_ca_system_score_gemma":0.002269489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00564882,"about_ca_topic_score_gemma":0.005301626,"domain_scores_codex":[0.9988398,0.000372119,0.00007445077,0.0002260111,0.0003582127,0.0001295706],"domain_scores_gemma":[0.9963608,0.002668503,0.0002575638,0.0002408618,0.0003789416,0.00009345527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006371096,0.00005022582,0.0002533371,0.0001161167,0.00003393921,0.00003807912,0.0000760825,0.7816207,0.0006872373,0.1264684,0.001871674,0.08872044],"study_design_scores_gemma":[0.0000203656,0.00001002617,0.00002664799,0.0000109282,0.000003520748,0.000009450943,0.000004121474,0.9577761,0.000173327,0.04122607,0.0007340824,0.000005444259],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0015614,0.0002569109,0.9965584,0.00009934732,0.00003653101,0.00004375956,0.0000230258,0.0002535771,0.001166958],"genre_scores_gemma":[0.2679682,0.001142053,0.723323,0.0002128847,0.0001898569,0.001070625,0.0002935219,0.0002121597,0.005587706],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006147014,"threshold_uncertainty_score":0.02056384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02201706201798436,"score_gpt":0.2565755941705012,"score_spread":0.2345585321525168,"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."}}