{"id":"W4401024755","doi":"10.24963/ijcai.2024/634","title":"A Primal-dual Perspective for Distributed TD-learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Natural Science Foundation of China; Tencent","keywords":"Inference; Computer science; Natural language processing; Language model; Artificial intelligence","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":[0.002626429,0.0009499975,0.001127276,0.0004131329,0.000365408,0.001280678,0.001331257,0.001230667,0.002778665],"category_scores_gemma":[0.005701737,0.0004137484,0.0006933272,0.0005797443,0.001463231,0.001458458,0.001504338,0.00232624,0.0002644927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001138316,"about_ca_system_score_gemma":0.001327094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001997273,"about_ca_topic_score_gemma":0.001264737,"domain_scores_codex":[0.9994107,0.0002760861,0.00002363902,0.0001123052,0.0001260864,0.00005118856],"domain_scores_gemma":[0.9978107,0.001525879,0.0001649347,0.00010131,0.0002972538,0.00009994018],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004640596,0.00004152593,0.0003160538,0.0001034498,0.00003220589,0.00005001346,0.00004999338,0.8412625,0.0006046244,0.1456979,0.0007250389,0.01107032],"study_design_scores_gemma":[0.00000410142,0.00001170293,0.00001438244,0.000004379191,0.000002594253,0.000007011006,0.000004613743,0.9815933,0.0001007915,0.0179711,0.0002837261,0.000002247622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002920987,0.0002383017,0.9949084,0.000289222,0.0000441125,0.00001448234,0.0000167886,0.00001934889,0.001548287],"genre_scores_gemma":[0.6984452,0.001075326,0.2916904,0.0004127321,0.0002839167,0.0002825327,0.0001118582,0.00009738876,0.007600713],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002778665,"threshold_uncertainty_score":0.01389009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02053758923025389,"score_gpt":0.2842636548327588,"score_spread":0.2637260656025049,"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."}}