{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004252117,0.000129318,0.0001438933,0.00007905825,0.0001485246,0.0001072535,0.0003998385,0.0000426023,0.00002481007],"category_scores_gemma":[0.0001207615,0.0001155001,0.00007977774,0.000188528,0.00003403328,0.0001012845,0.00004075827,0.00007636708,0.00004255534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005989695,"about_ca_system_score_gemma":0.000106013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002480258,"about_ca_topic_score_gemma":4.85525e-7,"domain_scores_codex":[0.9987866,0.00006323284,0.0002294217,0.0002967104,0.0003176035,0.0003064146],"domain_scores_gemma":[0.9989253,0.0004198966,0.00009470746,0.0002587444,0.0002157402,0.00008558474],"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":[0.000003223381,0.00001795805,0.00002038657,0.00000225355,0.00001678879,0.000001001494,0.00008337567,0.6459559,0.00001199585,0.3517608,0.000369579,0.001756815],"study_design_scores_gemma":[0.001107283,0.0001789424,0.0003450191,0.000005145474,0.000005403013,0.00000530934,0.00004274041,0.9950352,0.0001049258,0.0005098706,0.00250635,0.0001537972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009969076,0.00001689431,0.9862167,0.0003681872,0.0003563379,0.0005055025,0.000002224552,0.0001537701,0.01228064],"genre_scores_gemma":[0.4333314,5.927329e-7,0.5630177,0.0008122992,0.00003023552,0.00003452395,0.000002876245,0.000008658541,0.002761687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4332317,"threshold_uncertainty_score":0.4709957,"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."}}