{"id":"W2102847492","doi":"10.1145/1390156.1390286","title":"Apprenticeship learning using linear programming","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Apprenticeship; Markov decision process; Computer science; Linear programming; Solver; Frame (networking); Markov process; Mathematical optimization; Process (computing); Markov chain; Artificial intelligence; Machine learning; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002190368,0.000120148,0.0001174947,0.00009438318,0.00036778,0.0001091385,0.0005981284,0.00005029282,0.00003030289],"category_scores_gemma":[0.0001003205,0.0001122962,0.00005762203,0.0004000482,0.00005220264,0.0005436887,0.0002881753,0.0002565385,0.000129726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003284488,"about_ca_system_score_gemma":0.00005401459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002577154,"about_ca_topic_score_gemma":4.463867e-7,"domain_scores_codex":[0.9987568,0.00005713522,0.0002136119,0.0002730321,0.0003440049,0.0003553867],"domain_scores_gemma":[0.999343,0.00006244618,0.0001051711,0.0003339181,0.00006871622,0.0000867997],"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":[0.000001128855,0.00001479226,0.01391528,0.000011243,0.00001143352,0.00002560094,0.0007192069,0.9762692,0.0002105855,0.003872871,0.00004250978,0.004906121],"study_design_scores_gemma":[0.0001420662,0.0000529735,0.0004208586,0.00001149192,0.000003455639,0.00006403509,0.00003248982,0.9878993,0.0004858464,0.00001288818,0.01071963,0.0001549848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02527485,0.00002128833,0.9683531,0.00006256111,0.0001892532,0.0001043227,1.036349e-8,0.0005239496,0.00547068],"genre_scores_gemma":[0.5470853,0.00000504924,0.4498993,0.00007084916,0.00006273286,0.000002121358,8.50477e-7,0.000009465325,0.002864302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5218105,"threshold_uncertainty_score":0.4579307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06668564856124883,"score_gpt":0.2809145654987666,"score_spread":0.2142289169375178,"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."}}