{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002336715,0.00007232249,0.00009641631,0.00006678815,0.00003387792,0.00002551617,0.0004125451,0.00004055957,0.0001128919],"category_scores_gemma":[0.00008052866,0.00006206441,0.00003174287,0.0002616215,0.00002204087,0.0005086758,0.0002301074,0.00006613399,0.00002410367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002559237,"about_ca_system_score_gemma":0.00002516989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001848907,"about_ca_topic_score_gemma":6.59405e-7,"domain_scores_codex":[0.9992147,0.00003318895,0.0002078342,0.0001082967,0.0002259636,0.000210014],"domain_scores_gemma":[0.9993339,0.00005099435,0.000103502,0.000368058,0.00007880032,0.00006478967],"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":[8.419466e-7,0.00003023711,0.001495677,0.000007014293,0.000005355377,1.831532e-7,0.0001808151,0.9836289,0.00002322582,0.01328964,0.0005780281,0.0007601118],"study_design_scores_gemma":[0.0001100378,0.00003711744,0.0005428003,0.00000864001,0.000003226661,0.000002382061,0.00002813195,0.9981081,0.0002675766,0.00001885916,0.000795018,0.00007804723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002761885,0.0000303442,0.9858996,0.0002701985,0.0002491599,0.00006882634,3.287953e-7,0.0001048497,0.01310052],"genre_scores_gemma":[0.248199,0.00001501889,0.7494946,0.0001722492,0.00006194045,0.000001249925,0.000008765715,0.000005911367,0.002041342],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2479228,"threshold_uncertainty_score":0.2530913,"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."}}