{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002275392,0.0008380432,0.001852392,0.0006059943,0.0004584827,0.0006188771,0.00154154,0.001304136,0.00273263],"category_scores_gemma":[0.00939098,0.0006320017,0.0006538919,0.0005692418,0.001264361,0.001612104,0.001425893,0.002440488,0.000505085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001057736,"about_ca_system_score_gemma":0.001716992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004357251,"about_ca_topic_score_gemma":0.003776343,"domain_scores_codex":[0.9990432,0.0004053103,0.0000577068,0.0002101834,0.0002047672,0.00007882967],"domain_scores_gemma":[0.9939134,0.004354985,0.0004044182,0.0006978682,0.0004779579,0.0001514277],"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":[0.0001029656,0.0001133528,0.0006252574,0.0001023463,0.00006680322,0.00005087183,0.00006111086,0.9012827,0.000886254,0.01747866,0.001594215,0.0776355],"study_design_scores_gemma":[0.000007466238,0.00000943667,0.00002512649,0.000002856709,0.00000237598,0.000003422471,0.000001285053,0.9942529,0.0001540956,0.005431781,0.0001071109,0.000002063728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01081488,0.0002381184,0.9869968,0.0001917712,0.00003592552,0.00004537749,0.00003287656,0.0006053786,0.001038935],"genre_scores_gemma":[0.8439763,0.0003260119,0.1523244,0.0002269341,0.0001112912,0.0003390511,0.0002037987,0.0001535935,0.002338571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004357251,"threshold_uncertainty_score":0.01203358,"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."}}