{"id":"W2950989964","doi":"","title":"Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Function (biology); Artificial intelligence; Mathematical optimization; Inverse; Apprenticeship; Gradient method; Machine learning; Algorithm; Markov process; Mathematics; Statistics","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":[0.001418825,0.001067773,0.001256839,0.0005963118,0.0003166953,0.0007622296,0.001609225,0.001263837,0.001972753],"category_scores_gemma":[0.004439262,0.0005386878,0.0005127872,0.0003153037,0.001257264,0.001285434,0.001343169,0.001504122,0.000479616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005795319,"about_ca_system_score_gemma":0.0009312978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002240029,"about_ca_topic_score_gemma":0.001558557,"domain_scores_codex":[0.99936,0.0002346768,0.00003494666,0.00014682,0.0001632099,0.00006039918],"domain_scores_gemma":[0.9985563,0.0008594098,0.0001464858,0.0001259374,0.0002224045,0.00008942177],"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":[0.00008001884,0.0001398748,0.0009395681,0.0001167724,0.00006286935,0.0000988031,0.0001118207,0.8601521,0.002133981,0.02660183,0.0009275468,0.1086348],"study_design_scores_gemma":[0.0000108555,0.00003463747,0.00005502873,0.000005301348,0.000003383343,0.00001539534,0.000003671233,0.9935675,0.0004297769,0.005512306,0.0003575398,0.000004682744],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009749476,0.0002141774,0.9881891,0.00009499514,0.00002814346,0.000041877,0.00000711133,0.0002303382,0.001444885],"genre_scores_gemma":[0.6465748,0.0003161742,0.3481191,0.0001595343,0.00007012788,0.000229811,0.00006027038,0.0001038923,0.004366305],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002240029,"threshold_uncertainty_score":0.007503569,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1364476977309777,"score_gpt":0.2590478520903364,"score_spread":0.1226001543593586,"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."}}