{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003053192,0.0006131054,0.0007350025,0.0002119823,0.0001937531,0.0007796955,0.0007591365,0.0006222563,0.007030945],"category_scores_gemma":[0.001309772,0.0003502865,0.0004356333,0.0003500147,0.0005699992,0.00112211,0.000670508,0.001508436,0.001114972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007088978,"about_ca_system_score_gemma":0.0004492193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001998215,"about_ca_topic_score_gemma":0.002342145,"domain_scores_codex":[0.9997979,0.00006471359,0.000008063455,0.00003176443,0.00008217776,0.00001541873],"domain_scores_gemma":[0.9996905,0.0002226278,0.00001670895,0.00003227789,0.00002888563,0.000009102766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003292043,0.00004777208,0.0001369107,0.0002681352,0.00003912214,0.00008133189,0.00007760343,0.3646082,0.001628117,0.4348553,0.01358848,0.1846361],"study_design_scores_gemma":[0.00000945085,0.0000170802,0.00008082596,0.0000357414,0.000006416428,0.00003125991,0.00000777213,0.7107845,0.0003943494,0.2776775,0.01094524,0.000009936555],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003232622,0.003486349,0.9660266,0.0005108954,0.000164308,0.00002227406,0.0001165575,0.0004729126,0.02596748],"genre_scores_gemma":[0.531077,0.01016099,0.352825,0.0003632373,0.0005131467,0.0003596609,0.001016139,0.0003565697,0.1033283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007030945,"threshold_uncertainty_score":0.02352083,"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."}}