{"id":"W4404815779","doi":"10.1093/pnasnexus/pgae540","title":"Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning","year":2024,"lang":"en","type":"article","venue":"PNAS Nexus","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Japan Society for the Promotion of Science; Japan Society for the Promotion of Science London; Japan Agency for Medical Research and Development","keywords":"Term (time); Reinforcement; Reinforcement learning; Psychology; Cognitive psychology; Computer science; Artificial intelligence; Social psychology; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003164302,0.0002476829,0.0002013262,0.0003081016,0.0003063232,0.0007955828,0.0006075077,0.00008464452,0.00009233502],"category_scores_gemma":[0.00005399047,0.0002584093,0.0001274468,0.0005254742,0.00004188891,0.0009148838,0.0003384818,0.0004831989,0.0001884775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000264847,"about_ca_system_score_gemma":0.0001371277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000306754,"about_ca_topic_score_gemma":0.000001880016,"domain_scores_codex":[0.9977511,0.00006559004,0.0004656062,0.0004977256,0.0006867481,0.0005332874],"domain_scores_gemma":[0.9991875,0.000106714,0.00007059146,0.0003911475,0.00009801062,0.000146007],"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":[0.000002789445,0.00001451134,0.0005023884,0.0001086188,0.00003046795,0.0001269889,0.000833787,0.9886747,0.0003087318,0.00636872,0.0000108563,0.003017462],"study_design_scores_gemma":[0.0002186265,0.00009550861,0.0001096347,0.0002701821,0.00003738551,0.00007693042,0.00004144734,0.9983129,0.0001126082,0.0002974757,0.00012842,0.000298868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04854732,0.0006975355,0.9483778,0.0001070914,0.0008479847,0.0002192182,3.85507e-7,0.0005047694,0.0006978334],"genre_scores_gemma":[0.974016,0.00004485114,0.02482117,0.00009824531,0.0001605413,0.00002057246,0.00003161518,0.00003663323,0.0007704153],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9254686,"threshold_uncertainty_score":0.9999868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03408225842641407,"score_gpt":0.2961966146611672,"score_spread":0.2621143562347531,"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."}}