{"id":"W4401813166","doi":"10.1162/neco_a_01698","title":"Active Inference and Reinforcement Learning: A Unified Inference on Continuous State and Action Spaces Under Partial Observability","year":2024,"lang":"en","type":"article","venue":"Neural Computation","topic":"Embodied and Extended Cognition","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Observability; Inference; Reinforcement learning; Action (physics); Artificial intelligence; Machine learning; State (computer science); Computer science; Mathematics; Algorithm; Applied mathematics; Physics","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":[0.004151096,0.001554282,0.002298003,0.001480306,0.0006951583,0.002754256,0.003878054,0.00213104,0.002251769],"category_scores_gemma":[0.01273511,0.00110008,0.002025618,0.001300728,0.003510179,0.004455434,0.003823263,0.004527955,0.0004025622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001950607,"about_ca_system_score_gemma":0.002927723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007050955,"about_ca_topic_score_gemma":0.004804756,"domain_scores_codex":[0.997099,0.0009942079,0.0001598208,0.0007601116,0.0007425801,0.0002442032],"domain_scores_gemma":[0.993386,0.004705629,0.0006263016,0.0004614374,0.0005380461,0.0002824885],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007490497,0.00006726692,0.0007785097,0.000166888,0.0001065543,0.0001420286,0.0001856276,0.7521709,0.0008739995,0.2107721,0.0009186362,0.03374268],"study_design_scores_gemma":[0.000009916504,0.00002394747,0.00006386102,0.0000189991,0.00001256489,0.00001219401,0.000006206879,0.9476001,0.0001688637,0.05162096,0.0004523383,0.00001010798],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002226324,0.0003188524,0.9959685,0.0002031973,0.00003050298,0.00002368413,0.00003915361,0.00009757958,0.00109223],"genre_scores_gemma":[0.579784,0.002006305,0.4125712,0.0003709363,0.0004518106,0.000502588,0.000359423,0.000172692,0.003781131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007050955,"threshold_uncertainty_score":0.02195334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09609533118337915,"score_gpt":0.345143274593312,"score_spread":0.2490479434099328,"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."}}