{"id":"W2766724300","doi":"10.1016/j.ifacol.2017.08.1326","title":"On Synchronous Binary Log-Linear Learning and Second Order Q-learning","year":2017,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Game Theory and Applications","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Binary number; Computer science; Focus (optics); Artificial intelligence; Algorithm; Log-linear model; Q-learning; Binary search algorithm; Binary classification; Order (exchange); Mathematics; Machine learning; Linear model; Search algorithm; Reinforcement learning; Arithmetic","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":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001461659,0.0002099344,0.0003098597,0.0001305988,0.001692007,0.0003686291,0.0006856809,0.000120961,0.002874964],"category_scores_gemma":[0.003922219,0.0001625259,0.00007802414,0.0001813522,0.0003374265,0.0002875886,0.0002604866,0.0005797062,0.001382371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021994,"about_ca_system_score_gemma":0.00004965655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000152791,"about_ca_topic_score_gemma":0.00003460554,"domain_scores_codex":[0.9980227,0.0001937748,0.0003533306,0.000630265,0.000477432,0.0003224756],"domain_scores_gemma":[0.9974285,0.001182462,0.0003519036,0.0007002267,0.0001651252,0.0001717169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008314922,0.001098734,0.065243,0.00008129235,0.0002488321,0.0002864455,0.007935498,0.02171864,0.09531128,0.03666661,0.000595017,0.7699832],"study_design_scores_gemma":[0.007824146,0.004034689,0.1758805,0.0003983651,0.0002046733,0.0003411079,0.01677467,0.2285293,0.005436007,0.06515373,0.4919327,0.003490178],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9769777,0.0001347331,0.0007882878,0.002197714,0.0001439013,0.0001569762,0.00001664672,0.00008798041,0.01949606],"genre_scores_gemma":[0.945557,0.00002770819,0.01683789,0.0002839854,0.0002138968,0.00001267121,0.00001360846,0.00002412967,0.03702909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.766493,"threshold_uncertainty_score":0.9996077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05183597797220337,"score_gpt":0.3817292613896204,"score_spread":0.3298932834174171,"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."}}