{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009939585,0.0001404964,0.0001165727,0.00007893153,0.0001826791,0.0002807144,0.00003680968,0.00004515209,0.00001094835],"category_scores_gemma":[0.0002880437,0.0001258832,0.00001998904,0.0001607289,0.0001034229,0.0004729339,0.00004498915,0.0002875084,0.00001817385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004313571,"about_ca_system_score_gemma":0.00003045427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004331386,"about_ca_topic_score_gemma":0.00001447289,"domain_scores_codex":[0.9988655,0.0001758214,0.0001657147,0.000416931,0.0002046981,0.0001713035],"domain_scores_gemma":[0.9990989,0.0006561884,0.00007019102,0.00005861097,0.0000493055,0.00006682844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001001827,0.0001098561,0.001296207,0.0003126415,0.00002410064,0.00004312576,0.005092528,0.2626356,0.082248,0.07493079,0.00003883471,0.5722665],"study_design_scores_gemma":[0.0005642739,0.00105275,0.01237819,0.0001091106,0.00002623905,0.00001445542,0.0004270443,0.8573847,0.04474555,0.08284321,0.0001682642,0.0002861838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909415,0.00001456503,0.006069605,0.0005463176,0.0002453355,0.000249208,0.00000369917,0.0001562728,0.001773561],"genre_scores_gemma":[0.99948,0.00007720336,0.00002328766,0.000233406,0.00003463341,0.00001514892,0.00001226582,0.000008793442,0.0001152472],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5947492,"threshold_uncertainty_score":0.5133368,"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."}}