{"id":"W1537974983","doi":"","title":"Reinforcement using supervised learning for policy generalization","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Reinforcement learning; Markov decision process; Bellman equation; Computer science; Function approximation; Q-learning; Artificial intelligence; Mathematical optimization; Temporal difference learning; Generalization; Machine learning; Formalism (music); Markov process; Mathematics; Artificial neural network","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":[0.0006318938,0.0001265613,0.0001114992,0.0002584551,0.0002492219,0.0001657594,0.000418537,0.00006072238,0.00001903349],"category_scores_gemma":[0.0001608256,0.000123145,0.00006443405,0.0004843304,0.00001994142,0.0004390026,0.0001567413,0.00008255894,0.00001519406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001844304,"about_ca_system_score_gemma":0.000106926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001014844,"about_ca_topic_score_gemma":0.0000028852,"domain_scores_codex":[0.9986839,0.00002147975,0.0003342241,0.0002360277,0.0002824353,0.0004418897],"domain_scores_gemma":[0.9992668,0.00008355009,0.0001113121,0.0002978736,0.0001473868,0.00009308148],"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":[0.00000367981,0.000003523224,0.0004575152,0.00001007959,0.000007912501,6.566333e-7,0.0002073967,0.8415167,0.002878574,0.1520074,0.00006878794,0.002837676],"study_design_scores_gemma":[0.0003885152,0.00009569419,0.0001295517,0.000008347268,0.00000409566,0.000003647922,0.00002654132,0.9852433,0.005767987,0.0002120519,0.007960333,0.0001599316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002258697,0.000008156542,0.9906393,0.0002610655,0.0002001602,0.0002831776,4.473869e-8,0.0002454444,0.006103928],"genre_scores_gemma":[0.625504,0.000005786128,0.3679814,0.0007283165,0.0002404141,0.00000460142,0.00001182743,0.00001706127,0.005506632],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6232453,"threshold_uncertainty_score":0.5021709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03822809926627745,"score_gpt":0.3112965769924141,"score_spread":0.2730684777261366,"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."}}