{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176532,0.000465434,0.0004358391,0.0003749336,0.0002885121,0.0008413358,0.0007399456,0.0008771055,0.001438157],"category_scores_gemma":[0.004811076,0.0002290446,0.0003989544,0.0003308027,0.001740725,0.001665409,0.001200413,0.001223332,0.0001721443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036305,"about_ca_system_score_gemma":0.0005491109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002688494,"about_ca_topic_score_gemma":0.001234891,"domain_scores_codex":[0.9997146,0.0001080998,0.00001469134,0.00005154055,0.00008249693,0.00002869049],"domain_scores_gemma":[0.9989017,0.0007113237,0.0001299954,0.00005861228,0.0001297597,0.00006845108],"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":[0.00005450761,0.00002042054,0.0005840076,0.00007312891,0.00002203839,0.0001031324,0.0001528732,0.3684017,0.003223454,0.6165454,0.0003768418,0.0104425],"study_design_scores_gemma":[0.000003539582,0.00001211201,0.00003248544,0.000003733936,0.000001716806,0.000009731145,0.000006224435,0.9431657,0.0003012436,0.05610696,0.0003529988,0.00000360629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04010224,0.0004969334,0.9521387,0.0006821062,0.00009088498,0.0000288658,0.00003176855,0.00006302453,0.006365419],"genre_scores_gemma":[0.8989486,0.0005876287,0.09167749,0.0002131996,0.0001044488,0.00009714167,0.00006110391,0.00004950725,0.008260894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002688494,"threshold_uncertainty_score":0.007518947,"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."}}