{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001474608,0.0005630098,0.0005402997,0.0004958343,0.0005750607,0.0003748061,0.001344087,0.000399838,0.00005505381],"category_scores_gemma":[0.0002223023,0.0006759925,0.0002294142,0.000619826,0.0001974838,0.0008389332,0.005323416,0.002033425,0.00004950899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004419858,"about_ca_system_score_gemma":0.0001451501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001343765,"about_ca_topic_score_gemma":0.000003346225,"domain_scores_codex":[0.9963731,0.0008918702,0.0004344121,0.001224298,0.0002261579,0.0008502132],"domain_scores_gemma":[0.9973782,0.0002983283,0.0008378954,0.0009029378,0.000168731,0.0004138949],"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":[0.00001304878,0.00001895257,0.00899232,0.0001757151,0.0001389894,0.00004153966,0.001192594,0.967137,0.0001077055,0.02118772,0.00001185321,0.0009825625],"study_design_scores_gemma":[0.0004462345,0.0000771894,0.0002427879,0.0001695974,0.0002063375,0.00001172248,0.0003162991,0.9944353,0.0001125674,0.0007576522,0.002528451,0.0006958364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05300454,0.0001487873,0.941695,0.00001825588,0.0009089616,0.0003571108,2.676032e-7,0.0003902204,0.00347687],"genre_scores_gemma":[0.9234815,0.0003207705,0.07206266,0.0000436228,0.0001066457,0.000001276588,0.00001638776,0.00004211989,0.003925072],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8704769,"threshold_uncertainty_score":0.9995691,"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."}}