{"id":"W4318829810","doi":"10.2139/ssrn.4229967","title":"Combining Information-Seeking Exploration and Reward Maximization: Unified Inference on Continuous State and Action Spaces Under Partial Observability","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Observability; Inference; Action (physics); Maximization; State (computer science); Utility maximization; Mathematical economics; Complete information; Computer science; Artificial intelligence; Psychology; Microeconomics; Social psychology; Economics; Mathematics; Algorithm; Applied 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":[0.00128724,0.0001210098,0.0001287047,0.0001275351,0.0007648512,0.0005298403,0.0002345411,0.00002877553,0.000007652469],"category_scores_gemma":[0.0001113218,0.0001236811,0.00002169484,0.0002455897,0.00003771135,0.002221758,0.0001890375,0.001051933,0.000002755792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004603609,"about_ca_system_score_gemma":0.0005414017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002692401,"about_ca_topic_score_gemma":0.00002830012,"domain_scores_codex":[0.9982416,0.0002213327,0.000323162,0.0001677486,0.0004031714,0.0006429715],"domain_scores_gemma":[0.9991975,0.0001241093,0.0003500047,0.000171195,0.00009864578,0.00005851172],"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":[0.00004987808,0.00001421978,0.003882199,0.000007380707,0.00003007013,7.423325e-7,0.002138442,0.8225785,0.00004026209,0.1519744,0.000008596374,0.01927532],"study_design_scores_gemma":[0.001466834,0.001557278,0.004887689,0.00002536477,0.00001891385,0.0001507824,0.007002911,0.8456278,0.00008783249,0.1373943,0.001433137,0.0003472283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1734851,0.00005148082,0.8244846,0.001478354,0.0002336324,0.0001237638,4.160659e-7,0.00004602924,0.00009659218],"genre_scores_gemma":[0.9983729,0.0005763783,0.0006763356,0.000188693,0.00002736337,0.0000101192,0.000006987074,0.000005937956,0.0001352659],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8248879,"threshold_uncertainty_score":0.5882695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03176676461939781,"score_gpt":0.2606905869329649,"score_spread":0.2289238223135671,"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."}}