{"id":"W2097113539","doi":"10.1613/jair.898","title":"Accelerating Reinforcement Learning through Implicit Imitation","year":2003,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of British Columbia","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Natural Sciences and Engineering Research Council of Canada","keywords":"Imitation; Reinforcement learning; Observability; Computer science; Convergence (economics); Action (physics); Space (punctuation); Artificial intelligence; State space; Reinforcement; Value (mathematics); Human–computer interaction; Machine learning; Psychology; Mathematics; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00631117,0.0001536442,0.0002507791,0.0004431295,0.0005890947,0.0007183951,0.001111902,0.000095398,0.0001312823],"category_scores_gemma":[0.00374955,0.0001367928,0.0001367768,0.001279598,0.0001224546,0.001501859,0.0001908028,0.001396905,0.0001742293],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002532483,"about_ca_system_score_gemma":0.0004110012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002620821,"about_ca_topic_score_gemma":0.00000234679,"domain_scores_codex":[0.9954541,0.0006783106,0.001170682,0.0002570804,0.001750634,0.0006891928],"domain_scores_gemma":[0.9964403,0.0009106894,0.0005219298,0.0003631251,0.001603974,0.0001599956],"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":[0.00001358498,0.00002792562,0.00009031263,0.00001211117,0.00002187909,0.00002348281,0.002549058,0.7210429,0.006099456,0.2478757,0.000119119,0.02212445],"study_design_scores_gemma":[0.00009995599,0.001855639,0.0000452787,0.0001654187,0.000009800402,0.0001402498,0.006143613,0.7771646,0.1509272,0.05645241,0.006663742,0.0003321527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007117496,0.0001014125,0.9806769,0.0005295918,0.0004407492,0.0001755816,4.165879e-8,0.00002476661,0.0109334],"genre_scores_gemma":[0.9279053,0.0001594595,0.0712276,0.00005820607,0.0001818653,0.000004634013,5.258775e-7,0.00001494361,0.0004474337],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9207879,"threshold_uncertainty_score":0.69275,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2541885736812509,"score_gpt":0.4324161648659641,"score_spread":0.1782275911847133,"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."}}