{"id":"W7124937367","doi":"10.1109/aeeca65693.2025.00156","title":"Research on Improving the AlphaZero Algorithm for Dots and Boxes Strategy Based on the Transformer Framework","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Monte Carlo tree search; Transformer; Encoder; Artificial neural network; Game theory; Potential game; Sequential game; Game complexity","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":[0.0009555157,0.0009259343,0.000911842,0.0006522086,0.0002905082,0.0008999282,0.001720805,0.0007954736,0.003026002],"category_scores_gemma":[0.003146676,0.0003914082,0.0005433658,0.0003398981,0.000962125,0.002309066,0.001130436,0.001530701,0.0005095126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000910083,"about_ca_system_score_gemma":0.0013269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004814589,"about_ca_topic_score_gemma":0.005615532,"domain_scores_codex":[0.9996954,0.0000727658,0.00001860174,0.00007327191,0.00008144907,0.00005852436],"domain_scores_gemma":[0.999306,0.0003606853,0.000067231,0.00008332616,0.0001191217,0.00006366013],"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":[0.000149658,0.0001117088,0.002317947,0.0001128969,0.00008109,0.00007066208,0.0001275741,0.7247211,0.006543077,0.05986759,0.001548748,0.2043479],"study_design_scores_gemma":[0.00001323194,0.00004744393,0.00007998252,0.000005443331,0.0000075417,0.00001586057,0.00000821746,0.9922428,0.0007962836,0.00638384,0.0003955358,0.000003863373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03249016,0.0001669083,0.9633243,0.0001348932,0.00004047522,0.00006875971,0.00002266259,0.0005672601,0.003184521],"genre_scores_gemma":[0.7349317,0.0002834758,0.2592629,0.0002373959,0.0000302141,0.0001399523,0.0001241272,0.0002393463,0.004750837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004814589,"threshold_uncertainty_score":0.01012301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1017224516812249,"score_gpt":0.3977893217815049,"score_spread":0.29606687010028,"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."}}