{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001698974,0.001259978,0.00116349,0.0005045889,0.0005508468,0.001111416,0.001754426,0.001565982,0.004719628],"category_scores_gemma":[0.006134431,0.0007459231,0.0007552595,0.0004689477,0.001288989,0.001908834,0.002486797,0.002874608,0.0008589837],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008756542,"about_ca_system_score_gemma":0.001401907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002640314,"about_ca_topic_score_gemma":0.002590836,"domain_scores_codex":[0.9989291,0.0004313433,0.00004962811,0.0002936368,0.0001788843,0.0001174421],"domain_scores_gemma":[0.9971083,0.002159883,0.0001546948,0.0001615151,0.0002787863,0.0001369018],"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":[0.0001041654,0.0002677435,0.0009396519,0.0001210812,0.00005076439,0.0001277712,0.0001699147,0.824541,0.0013003,0.03321979,0.001979405,0.1371785],"study_design_scores_gemma":[0.0000124906,0.00004377675,0.00003844101,0.000009801571,0.000004383404,0.0000185891,0.00001338601,0.981109,0.0007162297,0.01737904,0.0006501589,0.000004834195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01489309,0.0001905903,0.9809168,0.0002281713,0.00002122474,0.0000673989,0.00001861235,0.0005753303,0.003088772],"genre_scores_gemma":[0.545786,0.0003493213,0.4444511,0.000368574,0.00006750543,0.0005186318,0.0001895455,0.0002028939,0.008066266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004719628,"threshold_uncertainty_score":0.01578867,"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."}}