{"id":"W2919205453","doi":"10.48550/arxiv.1903.00194","title":"Should All Temporal Difference Learning Use Emphasis?","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Counterexample; Convergence (economics); Temporal difference learning; Computer science; Simple (philosophy); Class (philosophy); Artificial intelligence; Mathematics; Economics; Reinforcement learning; Epistemology; Discrete mathematics","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":[0.006048158,0.0007427351,0.001066266,0.0003588538,0.0007097326,0.002026428,0.002267323,0.002689776,0.007570968],"category_scores_gemma":[0.02751793,0.0003627762,0.0004935907,0.0005453008,0.002706529,0.007838259,0.00203888,0.004984076,0.002029027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001119188,"about_ca_system_score_gemma":0.001308533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002332069,"about_ca_topic_score_gemma":0.002128419,"domain_scores_codex":[0.9983119,0.0007648166,0.00008591962,0.0004110124,0.0003038965,0.0001224687],"domain_scores_gemma":[0.9934021,0.004153691,0.0002419815,0.001040865,0.0008194866,0.0003419196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005034421,0.000225499,0.003238301,0.0004562416,0.0001273406,0.0001221556,0.0003597276,0.04102469,0.003465953,0.4905991,0.01887289,0.4410048],"study_design_scores_gemma":[0.0001536746,0.0003787159,0.000879837,0.0002447818,0.00003759652,0.0001819056,0.0001829142,0.267859,0.004641149,0.6900384,0.03535214,0.00004994087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02381364,0.005085698,0.9069777,0.03307745,0.001889635,0.0001111747,0.0001230147,0.0008148619,0.02810682],"genre_scores_gemma":[0.6607624,0.003311453,0.2982968,0.01068205,0.001383519,0.0002977307,0.0002190515,0.0005500684,0.02449689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007570968,"threshold_uncertainty_score":0.03198612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1825729635131934,"score_gpt":0.2228682985839207,"score_spread":0.0402953350707273,"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."}}