{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005553326,0.001598055,0.004222459,0.001787111,0.0006812708,0.002533792,0.003427766,0.002829518,0.001660299],"category_scores_gemma":[0.02474521,0.002200088,0.002072498,0.001796853,0.002958906,0.006080254,0.004333419,0.003309085,0.000225434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001452012,"about_ca_system_score_gemma":0.002809031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007665965,"about_ca_topic_score_gemma":0.007357811,"domain_scores_codex":[0.9979671,0.0007688467,0.0001506157,0.0005396293,0.0003287462,0.0002451705],"domain_scores_gemma":[0.9799346,0.01696778,0.001103805,0.0007927079,0.0006419557,0.000559207],"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":[0.0002838233,0.0001513626,0.001816515,0.0001553276,0.0001914664,0.000101556,0.000108561,0.9360973,0.0006294463,0.03280362,0.0004627236,0.02719828],"study_design_scores_gemma":[0.00001079173,0.00001766941,0.0001093074,0.000005821737,0.000009402713,0.000004967945,0.000002813812,0.9824829,0.0000911081,0.01723287,0.00002594729,0.000006483211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03738445,0.0003902479,0.960816,0.000352864,0.00002530216,0.00003706854,0.00009177161,0.0001841587,0.0007181778],"genre_scores_gemma":[0.9105348,0.0003836489,0.08689348,0.000173609,0.0001515448,0.000173935,0.0003033741,0.00008607337,0.001299552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007665965,"threshold_uncertainty_score":0.02936912,"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."}}