{"id":"W4404871448","doi":"10.1109/lcsys.2024.3509815","title":"Gradient Flow Approximations in Temporal Difference Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Control Systems Letters","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Temporal difference learning; Flow (mathematics); Balanced flow; Computer science; Mathematics; Applied mathematics; Artificial intelligence; Mathematical analysis; Geometry; Reinforcement learning","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":[0.0002870285,0.0001718975,0.0001919619,0.0001694836,0.00006393164,0.0001376238,0.0001827988,0.0001343265,0.000005525669],"category_scores_gemma":[0.0000506739,0.0001660965,0.000106081,0.0001946847,0.00004451269,0.000005285418,0.00002837861,0.0003250756,0.00003595964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001009306,"about_ca_system_score_gemma":0.00007819259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001884619,"about_ca_topic_score_gemma":0.00006355068,"domain_scores_codex":[0.9984262,0.00022585,0.0002733358,0.0004478935,0.0002462803,0.0003804644],"domain_scores_gemma":[0.9995485,0.00002712012,0.00004013776,0.0002602406,0.00003699806,0.00008703826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003095247,0.00001594966,0.0001095594,0.00008870782,0.00006044378,0.00006051663,0.00007280132,0.06002941,0.9373396,0.00009081349,0.001042436,0.001058803],"study_design_scores_gemma":[0.00317036,0.0004172029,0.0006008258,0.0006263768,0.00006157385,0.0001559073,0.0001788163,0.8984311,0.03987786,0.00003286685,0.0555768,0.0008703811],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3589789,0.003660044,0.6331641,0.001335064,0.001617293,0.0008949974,0.00002999415,0.00008365129,0.0002359965],"genre_scores_gemma":[0.998389,0.00003329931,0.00007298034,0.0002361978,0.000361659,0.0002698008,0.00005568803,0.00003891066,0.0005424596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8974618,"threshold_uncertainty_score":0.6773218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008723473920063464,"score_gpt":0.2406941707102832,"score_spread":0.2319706967902197,"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."}}