{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002491199,0.0007013722,0.00106702,0.0005571924,0.0004482639,0.001165114,0.001293246,0.001047689,0.00433325],"category_scores_gemma":[0.00952285,0.0003048919,0.0004168275,0.0009429753,0.001768915,0.001956922,0.001345041,0.001534675,0.0006418579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001303481,"about_ca_system_score_gemma":0.001599749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003569598,"about_ca_topic_score_gemma":0.001941832,"domain_scores_codex":[0.998477,0.0007478478,0.0000555218,0.000230366,0.0002973544,0.0001919996],"domain_scores_gemma":[0.9942017,0.004410401,0.0003414258,0.0002751489,0.0005841272,0.0001871249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002151699,0.0001381394,0.0006983869,0.0002147118,0.00003882639,0.00008646332,0.0001105783,0.7093239,0.001733911,0.1892669,0.002518782,0.09565428],"study_design_scores_gemma":[0.00001568268,0.00004476172,0.00007930442,0.000006847433,0.00000355334,0.00001952489,0.000005062447,0.973999,0.0002836949,0.02504193,0.0004941127,0.000006589472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008427098,0.0004425907,0.9852414,0.0002933065,0.00006082533,0.00003944892,0.00002397431,0.0001184263,0.005352953],"genre_scores_gemma":[0.8584833,0.0008943223,0.1282937,0.0004065233,0.0002123696,0.0001954048,0.0000816798,0.00008039339,0.01135243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00433325,"threshold_uncertainty_score":0.01449621,"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."}}