{"id":"W4399828133","doi":"10.1007/978-3-031-54071-4_22","title":"Reinforcement Learning for Partially Observable Models","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Observable; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Physics; Social psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009342499,0.0006572201,0.0009635909,0.0002474385,0.0002572504,0.001003193,0.001330299,0.0004762265,0.0000300814],"category_scores_gemma":[0.00005085647,0.0006248917,0.0004670891,0.00006120934,0.00004543365,0.000504249,0.0003007988,0.000748935,0.00070496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003245033,"about_ca_system_score_gemma":0.0003067882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004307641,"about_ca_topic_score_gemma":0.000003572162,"domain_scores_codex":[0.996206,0.00004205786,0.001160077,0.00093611,0.0008998691,0.0007559045],"domain_scores_gemma":[0.9972788,0.0003204874,0.000673633,0.001147219,0.0003793433,0.0002005301],"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":[0.000009444318,0.000001301188,6.466987e-7,0.0002821856,0.0002110913,0.00001307835,0.00008308941,0.5271639,0.000009371398,0.4704048,0.001628542,0.0001925915],"study_design_scores_gemma":[0.0005515154,0.0002220014,1.037054e-7,0.0005595338,0.0001099841,0.000008053787,0.000005599295,0.6244504,0.000001986573,0.006111596,0.3675793,0.0003998688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[1.166276e-7,0.001782864,0.6842856,0.0001885046,0.002414158,0.001717545,0.000004864303,0.000515084,0.3090912],"genre_scores_gemma":[0.07204819,0.00007520263,0.001128017,0.0001836747,0.0007853753,0.0003841655,0.00004783604,0.0001458147,0.9252017],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6831576,"threshold_uncertainty_score":0.9996203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03749092506764354,"score_gpt":0.2404367188686295,"score_spread":0.2029457938009859,"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."}}