{"id":"W1541317966","doi":"10.1609/aaai.v24i1.7740","title":"Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Markov decision process; Minimax; Computer science; Mathematical optimization; Set (abstract data type); Computation; Parallels; Exploit; Mathematics; Markov process; Algorithm; Machine learning; Economics","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":[0.000732109,0.0002525479,0.0002978216,0.0004775964,0.0001997811,0.0003552574,0.001927381,0.0001429204,0.0000215452],"category_scores_gemma":[0.00116825,0.0002089099,0.0000951567,0.001640189,0.0003396465,0.0005431751,0.0006115006,0.0006494951,0.00003514067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001104573,"about_ca_system_score_gemma":0.0002695741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006387252,"about_ca_topic_score_gemma":0.0000487088,"domain_scores_codex":[0.9977816,0.00002809552,0.0007084955,0.0004453324,0.0005609053,0.000475561],"domain_scores_gemma":[0.998288,0.0001423901,0.0005325306,0.0003068382,0.0006413315,0.00008893226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003290078,0.0000705358,0.000625311,0.0000319181,0.00000803781,7.471086e-7,0.002210734,0.306659,0.09016816,0.5890369,0.00002716834,0.01112854],"study_design_scores_gemma":[0.00005172836,0.00008198752,0.0004644309,0.0001468023,0.000005235127,0.000007585079,0.0003295758,0.8605183,0.1006924,0.03747215,0.00001817526,0.0002115995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4623965,0.00000569461,0.5161762,0.005125727,0.0008815795,0.0007454656,0.000002306646,0.0001671327,0.01449936],"genre_scores_gemma":[0.9785025,0.000008654375,0.02105062,0.0001909018,0.00009255003,0.000009723738,5.76348e-7,0.00001556093,0.0001288686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5538593,"threshold_uncertainty_score":0.85191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1230832600318342,"score_gpt":0.3346686475142595,"score_spread":0.2115853874824253,"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."}}