{"id":"W115994101","doi":"","title":"Robust Online Optimization of Reward-Uncertain MDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Computer science; Leverage (statistics); Markov decision process; Minimax; Mathematical optimization; Set (abstract data type); Pruning; Computation; Artificial intelligence; Markov process; Machine learning; Mathematics; Algorithm","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":[0.00250605,0.001713811,0.002365828,0.0005727461,0.0004852835,0.001523806,0.001467164,0.001787874,0.002986636],"category_scores_gemma":[0.01156739,0.00104221,0.0009367567,0.0006363388,0.001601044,0.001901224,0.002112908,0.002718635,0.0003945986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002088375,"about_ca_system_score_gemma":0.00205205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004986176,"about_ca_topic_score_gemma":0.004374691,"domain_scores_codex":[0.9985618,0.0005311032,0.00007732256,0.0003240954,0.0002802625,0.0002254095],"domain_scores_gemma":[0.993991,0.004639748,0.0005563466,0.0003759193,0.0002420991,0.0001949565],"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":[0.00005402694,0.00002319091,0.0001575118,0.00004558692,0.00001480201,0.00002952858,0.00001792662,0.9867892,0.0002307585,0.007844491,0.0002413748,0.004551588],"study_design_scores_gemma":[0.00001082309,0.00001437999,0.00002803901,0.00000663936,0.000003319628,0.000004251143,0.000003253682,0.9928975,0.0001452706,0.006781269,0.0001024246,0.000002696083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0379571,0.0004388893,0.9550579,0.0004567178,0.00003754369,0.00008605087,0.0001800632,0.0005751606,0.005210506],"genre_scores_gemma":[0.8683033,0.0003563269,0.1275971,0.0001685738,0.00003894388,0.0002256799,0.0002768065,0.0001470728,0.002886244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004986176,"threshold_uncertainty_score":0.01515222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05854918816098995,"score_gpt":0.26757053188534,"score_spread":0.2090213437243501,"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."}}