{"id":"W1521332421","doi":"","title":"A Bayesian approach to imitation in reinforcement learning","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":"University of Toronto; University of British Columbia","funders":"","keywords":"Imitation; Computer science; Bayesian probability; Reinforcement learning; Artificial intelligence; Machine learning; Bayesian network; Bayesian inference; Social learning; Knowledge management; Psychology","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":[0.003823983,0.001282886,0.00160266,0.001055199,0.0007851289,0.001912528,0.002746112,0.002754516,0.00433686],"category_scores_gemma":[0.0144058,0.0008686144,0.001181233,0.001181771,0.004003905,0.004970582,0.002431743,0.003933884,0.0007880796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001709679,"about_ca_system_score_gemma":0.001360185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003614462,"about_ca_topic_score_gemma":0.0033153,"domain_scores_codex":[0.9970708,0.001615931,0.0001423709,0.0003629728,0.0006547975,0.0001530571],"domain_scores_gemma":[0.9938937,0.004614142,0.0004118411,0.0003620992,0.0004447962,0.0002733795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003768569,0.00003701601,0.0003039285,0.0001001293,0.00005667023,0.0001060481,0.0001975719,0.1501077,0.000439988,0.8260015,0.001410288,0.02120154],"study_design_scores_gemma":[0.00002566786,0.00003158153,0.00008647724,0.00002735886,0.00001875256,0.00004138155,0.00001690586,0.3373304,0.0001758787,0.6589066,0.003315965,0.00002308592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001698911,0.0009070921,0.990805,0.001076591,0.00008914612,0.00002261744,0.00003283878,0.00006561297,0.005302145],"genre_scores_gemma":[0.5481937,0.004754511,0.4296415,0.000964587,0.001082676,0.0006099602,0.0001498348,0.0001721018,0.01443121],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00433686,"threshold_uncertainty_score":0.02022338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01968977948553463,"score_gpt":0.2436488599454223,"score_spread":0.2239590804598877,"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."}}