{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01143313,0.001507925,0.001577027,0.0008216391,0.0006791665,0.002103598,0.001175678,0.001724571,0.002735811],"category_scores_gemma":[0.04198601,0.0009217853,0.001249803,0.0009218327,0.001741206,0.002667736,0.00255353,0.003180852,0.0004062632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003154615,"about_ca_system_score_gemma":0.002566503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002232675,"about_ca_topic_score_gemma":0.002337337,"domain_scores_codex":[0.9872334,0.008725257,0.0006006183,0.0009218833,0.001995203,0.000523652],"domain_scores_gemma":[0.9661788,0.02893035,0.001899513,0.001341015,0.0009995678,0.0006508022],"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":[0.0003249433,0.0001318848,0.0007171255,0.0002034964,0.00006373184,0.0001045988,0.0002231917,0.8742864,0.001652185,0.09275765,0.0008459125,0.02868896],"study_design_scores_gemma":[0.00003686524,0.00006065554,0.0001073743,0.00002378733,0.000009743308,0.00001861084,0.00001595092,0.9283013,0.0008517997,0.07011199,0.000448158,0.00001375172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01866696,0.0003169711,0.9776177,0.0004422876,0.00001983315,0.0001288502,0.0001125647,0.00027109,0.002423646],"genre_scores_gemma":[0.7222089,0.0005815595,0.2736367,0.0003022779,0.00006794183,0.0005904814,0.0003568036,0.0001388138,0.002116654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01143313,"threshold_uncertainty_score":0.06046492,"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."}}