{"id":"W185706336","doi":"","title":"Labeled Initialized Adaptive Play Q-learning for Stochastic Games","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Q-learning; Computer science; Context (archaeology); Process (computing); Artificial intelligence; Optimal stopping; Point (geometry); Mathematical optimization; Adaptive learning; Grid; Quality (philosophy); Mathematics; Reinforcement learning","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":[0.0007611099,0.0001563973,0.0001869233,0.0001492747,0.0001876813,0.0001319748,0.0005601041,0.00007490853,0.00005078949],"category_scores_gemma":[0.0004293052,0.0001422933,0.00007486472,0.0002845518,0.00004237862,0.0003191088,0.0001725872,0.0001999094,0.00008159103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005476308,"about_ca_system_score_gemma":0.0000604659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001048846,"about_ca_topic_score_gemma":0.00000488991,"domain_scores_codex":[0.9985598,0.00004010242,0.0003036941,0.0003129659,0.0002978473,0.0004855975],"domain_scores_gemma":[0.9984031,0.0009066876,0.000139956,0.0002810638,0.0001586511,0.0001105841],"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":[0.00006617391,0.00002049581,0.00009179988,0.00000922733,0.00004624641,0.00000772877,0.001139116,0.8157823,0.000495235,0.174312,0.0004938411,0.007535854],"study_design_scores_gemma":[0.001183337,0.0004681595,0.0002770737,0.0000227156,0.00001085688,0.000008691815,0.0001711104,0.9922735,0.001196997,0.0007062705,0.003419545,0.0002617215],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001045632,0.00001870878,0.98817,0.0001095748,0.0003350878,0.000362163,2.282827e-7,0.000401093,0.009557491],"genre_scores_gemma":[0.78347,0.000001196557,0.2114793,0.0003115243,0.00008727526,0.00001770924,0.000003824756,0.00001603706,0.004613122],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7824243,"threshold_uncertainty_score":0.5802553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0278985086208105,"score_gpt":0.2864012359353325,"score_spread":0.258502727314522,"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."}}