{"id":"W1552684655","doi":"","title":"Using linear programming for Bayesian exploration in Markov decision processes","year":2007,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Computer science; Bellman equation; Reinforcement learning; Mathematical optimization; Markov process; Linear programming; Machine learning; Representation (politics); Artificial intelligence; Markov chain; Key (lock); Bayesian probability; Partially observable Markov decision process; Markov model; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.001096714,0.0002063185,0.0001853076,0.0005098616,0.0001228865,0.0003920841,0.0008631855,0.00009992422,0.00003922663],"category_scores_gemma":[0.00135866,0.0002088903,0.00006751872,0.0005514615,0.00006652463,0.0009552589,0.0001460838,0.0002244475,0.00004868241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002109111,"about_ca_system_score_gemma":0.0002121952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003725875,"about_ca_topic_score_gemma":0.0002087822,"domain_scores_codex":[0.9975551,0.00003150483,0.0008522841,0.0005238088,0.0006356875,0.0004015567],"domain_scores_gemma":[0.9981309,0.0004177777,0.0002841508,0.0002984485,0.0007758776,0.00009280629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001515707,0.0001434433,0.0001790877,0.00002630882,0.00001243828,0.00002025599,0.0009005344,0.2799692,0.001970978,0.2238199,0.00001534535,0.492791],"study_design_scores_gemma":[0.00006143513,0.000167439,0.00005498284,0.0002708112,0.000002578771,0.000005763115,0.0003053287,0.9341963,0.03173863,0.03232767,0.0006380738,0.000231001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002407519,0.000006063945,0.9935604,0.001157994,0.001040565,0.0005269353,0.000001750407,0.0001044195,0.001194326],"genre_scores_gemma":[0.6714817,0.00001425085,0.3280916,0.0001732124,0.0001417479,0.00002705025,0.000008788706,0.00001179147,0.00004987633],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6690741,"threshold_uncertainty_score":0.8518301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2143689443380605,"score_gpt":0.3942220206217933,"score_spread":0.1798530762837328,"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."}}