{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005240345,0.0001861363,0.0001906465,0.0001600003,0.0002550803,0.0003631146,0.000960897,0.00009498983,0.00003223107],"category_scores_gemma":[0.0001276534,0.0001766212,0.0001202242,0.0008012557,0.00002782029,0.0003196055,0.0003224277,0.0001096696,0.0001443213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000837714,"about_ca_system_score_gemma":0.0002508277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004458323,"about_ca_topic_score_gemma":0.000002036195,"domain_scores_codex":[0.9980787,0.00003259417,0.0003586706,0.000484539,0.0004766324,0.0005688597],"domain_scores_gemma":[0.9986578,0.0003502677,0.0001096632,0.0006327239,0.0001506843,0.00009885523],"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":[0.000006638269,0.000009026882,0.000008666536,0.00001271375,0.00000954233,0.000009547284,0.00003316436,0.8807009,0.0001360972,0.002172535,0.002135038,0.1147661],"study_design_scores_gemma":[0.0005243,0.0001221565,0.00001556813,0.00003495096,0.00001298404,0.00000262922,0.000004711676,0.9963382,0.0003336014,0.001398577,0.0009807415,0.0002315841],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000252531,0.00001423744,0.9974443,0.0001183261,0.0005954048,0.0003530388,0.000002908278,0.0007497569,0.0004695235],"genre_scores_gemma":[0.05253511,0.000006083812,0.9448649,0.000482023,0.00008472506,0.00007931211,0.0000188186,0.0000270101,0.001902014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1156373,"threshold_uncertainty_score":0.7202405,"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."}}