{"id":"W7061544221","doi":"","title":"Regret-based Reward Elicitation for Markov Decision Processes","year":2014,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Magnetic confinement fusion research","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto","keywords":"Regret; Preference elicitation; Markov decision process; Minimax; Heuristics; Heuristic; Set (abstract data type); Range (aeronautics); Partially observable Markov decision process","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008953415,0.00171332,0.001814933,0.0008833921,0.0008722769,0.002472549,0.001503244,0.001903882,0.00463005],"category_scores_gemma":[0.03769743,0.0009813219,0.001556065,0.0009470874,0.002015128,0.002708144,0.002467774,0.003898104,0.0005965459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004475439,"about_ca_system_score_gemma":0.003142334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004562714,"about_ca_topic_score_gemma":0.004385977,"domain_scores_codex":[0.9930269,0.004311088,0.0002672044,0.0007128991,0.001198896,0.0004831069],"domain_scores_gemma":[0.9696973,0.0263373,0.001360873,0.001021877,0.001029067,0.0005535067],"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":[0.0001070461,0.00004776508,0.0003703564,0.00008106825,0.0000264099,0.00005348017,0.00009300736,0.9276183,0.0004290897,0.06129106,0.0005419151,0.009340513],"study_design_scores_gemma":[0.00001166534,0.00002067884,0.00004064881,0.00001209626,0.000004232158,0.00000806932,0.000008632943,0.9698569,0.0002126843,0.02956579,0.0002529471,0.000005696414],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01149776,0.0002226764,0.9839962,0.0004324064,0.00002534726,0.0001034589,0.00009682251,0.0002376358,0.003387747],"genre_scores_gemma":[0.6831396,0.0006319644,0.3103107,0.000340345,0.00009546805,0.0005719802,0.0003815444,0.0001808136,0.004347748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008953415,"threshold_uncertainty_score":0.0473507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0109746757051034,"score_gpt":0.2742549724037352,"score_spread":0.2632802966986318,"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."}}