{"id":"W4376639574","doi":"10.1145/3564246.3585161","title":"Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Google; National Science Foundation","keywords":"Observable; Computer science; Simple (philosophy); Class (philosophy); Reinforcement learning; Rank (graph theory); Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","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":[0.0022786,0.001227737,0.00146421,0.0007074482,0.0005183879,0.001475938,0.002577523,0.00161572,0.005917977],"category_scores_gemma":[0.00765771,0.000786729,0.0009412079,0.0008059692,0.001146041,0.002404128,0.003491579,0.003153398,0.001343093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0011222,"about_ca_system_score_gemma":0.002387388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001598687,"about_ca_topic_score_gemma":0.002421302,"domain_scores_codex":[0.9987842,0.0003876346,0.00006120263,0.0002289927,0.0003790008,0.000158981],"domain_scores_gemma":[0.997884,0.001316178,0.0001759389,0.0003490085,0.0001732022,0.0001016636],"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":[0.000227159,0.00009348316,0.0006620148,0.0001734604,0.00008526004,0.00009737059,0.0001140088,0.7502735,0.001502764,0.08963174,0.004778531,0.1523606],"study_design_scores_gemma":[0.00002577508,0.00002208153,0.00002990732,0.00001286731,0.000006362392,0.00002133132,0.000006494515,0.9624474,0.0004737214,0.03577906,0.001167867,0.00000712847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001758133,0.0001029234,0.9960136,0.0001717674,0.00002169629,0.0000344108,0.00005439947,0.0007777968,0.001065279],"genre_scores_gemma":[0.2899762,0.0002942259,0.7046993,0.0003746731,0.00009481724,0.0004120777,0.0003451762,0.000344369,0.003459149],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005917977,"threshold_uncertainty_score":0.01979756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07463704283305572,"score_gpt":0.3168502075495143,"score_spread":0.2422131647164585,"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."}}