{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005661552,0.0004218609,0.000319031,0.0003286451,0.002542193,0.002075879,0.002466067,0.0003438351,0.0002274398],"category_scores_gemma":[0.0006846945,0.0002259968,0.0002115687,0.001608154,0.001247974,0.0003332784,0.0001970706,0.001619635,0.00006529016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001197693,"about_ca_system_score_gemma":0.0007459733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004415396,"about_ca_topic_score_gemma":0.0001260303,"domain_scores_codex":[0.9951368,0.0007323773,0.000663844,0.001168433,0.001076275,0.00122226],"domain_scores_gemma":[0.9812871,0.01642353,0.00009628265,0.001535647,0.0005142859,0.0001431911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006003773,0.0001192521,0.000006718616,0.00002748205,0.00002754046,0.000002136155,0.000796764,0.0007149493,0.0001136621,0.3114381,0.00165476,0.6850386],"study_design_scores_gemma":[0.0001069442,0.00112834,0.00009737627,0.0003170539,0.00001965269,7.268706e-7,0.003088391,0.8354262,0.04994434,0.1066022,0.003033894,0.0002348364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002152776,0.0004179027,0.9356076,0.04767837,0.0009457306,0.00239116,0.00001993474,0.00006664096,0.01071993],"genre_scores_gemma":[0.9709024,0.0001249952,0.01848196,0.006422793,0.0002905923,0.0003794795,8.809007e-7,0.00002887732,0.003368011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9687496,"threshold_uncertainty_score":0.9989601,"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."}}