{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001563338,0.00006987424,0.00007109273,0.00004485022,0.00007320002,0.0002486449,0.000213574,0.00003053501,0.00002381308],"category_scores_gemma":[0.0000763935,0.00005859103,0.00005766974,0.0001789949,0.00001030698,0.0002550012,0.000122824,0.000111266,0.00003727272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009555101,"about_ca_system_score_gemma":0.00009651209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003563063,"about_ca_topic_score_gemma":0.000003458707,"domain_scores_codex":[0.9992566,0.00001562467,0.0000940539,0.0003398189,0.0001107749,0.0001831674],"domain_scores_gemma":[0.999597,0.0001180383,0.00001145869,0.0001648068,0.00007463192,0.00003406666],"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":[0.00000149844,0.000007602571,0.00001803182,0.00001273224,0.00001485329,0.000007945658,0.001002877,0.0008452224,0.0001870906,0.9852289,0.001139458,0.01153377],"study_design_scores_gemma":[0.000105236,0.00004829799,0.0000494524,0.00001504464,0.0000043741,0.00001115135,0.0003187553,0.9526319,0.0005004887,0.01497215,0.0312416,0.0001015819],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000974933,0.0001749678,0.9872366,0.003192396,0.0002749804,0.0001317565,0.000003390956,0.0006132119,0.007397777],"genre_scores_gemma":[0.8696384,0.000002035754,0.1279773,0.0001107269,0.0001384903,0.00002470116,0.000003761315,0.00000712723,0.002097504],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9702567,"threshold_uncertainty_score":0.2397688,"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."}}