{"id":"W9932698","doi":"10.48550/arxiv.1205.2619","title":"Regret-based Reward Elicitation for Markov Decision Processes","year":2012,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Markov decision process; Computer science; Preference elicitation; Function (biology); Minimax; Preference; Markov process; Markov chain; Mathematical optimization; Machine learning; Mathematics; Economics; Microeconomics","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":[0.001253235,0.0002091232,0.0002104733,0.0002943731,0.0001690765,0.0001853213,0.000864263,0.0001195639,0.00002927518],"category_scores_gemma":[0.00340313,0.0001980682,0.00007388119,0.001069128,0.00008641126,0.0006849042,0.00009730591,0.0001855271,0.0001174913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001913796,"about_ca_system_score_gemma":0.000198879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006058887,"about_ca_topic_score_gemma":0.00008485498,"domain_scores_codex":[0.9977805,0.00007609058,0.0006583534,0.0003969138,0.0004505945,0.0006375163],"domain_scores_gemma":[0.9971154,0.001666937,0.0002077292,0.0005200125,0.0003607238,0.0001292467],"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":[0.00008674122,0.0000885804,0.0009281563,0.00006248597,0.000004225817,0.000001190737,0.001179174,0.7760761,0.000173311,0.03872203,0.0001767744,0.1825013],"study_design_scores_gemma":[0.00006960314,0.0001709705,0.0001921221,0.0001483679,0.000005887343,0.000001682434,0.0002495141,0.9661885,0.01221098,0.01719148,0.003266823,0.0003040811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006224458,0.0001005677,0.9910662,0.0006289717,0.0008009584,0.0005801766,0.000002140948,0.0001426596,0.0004539385],"genre_scores_gemma":[0.8359503,0.00001535571,0.1633287,0.0003666744,0.0001428577,0.0001002042,0.00001274772,0.00001530113,0.00006795394],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8297258,"threshold_uncertainty_score":0.8076988,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06076316977610513,"score_gpt":0.3316740532104062,"score_spread":0.2709108834343011,"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."}}