{"id":"W2767141304","doi":"10.1109/cig.2017.8080452","title":"Improving hearthstone AI by learning high-level rollout policies and bucketing chance node events","year":2017,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Monte Carlo tree search; Entertainment; Adversary; Video game; State (computer science); Node (physics); Artificial intelligence; Game tree; Action (physics); Computer security; Sequential game; Multimedia; Game theory; Programming language; Monte Carlo method; Mathematical economics; Engineering; Visual arts","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":[0.001403184,0.001007297,0.000939135,0.0005636839,0.0005762532,0.001242948,0.001775758,0.001480638,0.005104504],"category_scores_gemma":[0.008092452,0.0005078858,0.0005564857,0.0003450983,0.00137514,0.002694502,0.002087202,0.002697247,0.0007138644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001175786,"about_ca_system_score_gemma":0.001583141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006245478,"about_ca_topic_score_gemma":0.01097483,"domain_scores_codex":[0.9993641,0.0001956436,0.00002715313,0.000162167,0.0001463668,0.0001045737],"domain_scores_gemma":[0.9974138,0.001826572,0.0001511659,0.0002430932,0.0001644791,0.0002010387],"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":[0.0002806054,0.0002594257,0.00298525,0.000111508,0.00007233264,0.00009257152,0.0002025777,0.8564065,0.00284044,0.02438855,0.00321066,0.1091496],"study_design_scores_gemma":[0.00002239518,0.00005045301,0.0001255217,0.000006888474,0.000006843216,0.00001180833,0.00001594606,0.9907743,0.0004925121,0.007827696,0.0006606702,0.000004894779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.129394,0.0005781612,0.8488069,0.001015957,0.000145527,0.0002858776,0.0001766439,0.003844736,0.01575211],"genre_scores_gemma":[0.8177584,0.0002598523,0.1751782,0.0005043367,0.00004723514,0.0001800116,0.0003026042,0.0002255596,0.005543885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006245478,"threshold_uncertainty_score":0.01707631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03426155760626678,"score_gpt":0.3060478462723761,"score_spread":0.2717862886661093,"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."}}