{"id":"W4387394614","doi":"10.1609/aiide.v19i1.27518","title":"Playing Various Strategies in Dominion with Deep Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Heuristics; Artificial intelligence; Simple (philosophy); Multiset; Set (abstract data type); Representation (politics); Dominion; Machine learning; Human–computer interaction; Mathematics; Programming language","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":[0.0003106828,0.0002948311,0.0002923313,0.0003140813,0.0001963023,0.000926353,0.0009028989,0.00006548652,0.00002105817],"category_scores_gemma":[0.0002157746,0.0002091379,0.00008183096,0.0007128142,0.0002582556,0.001972173,0.0005452859,0.000404536,0.000068734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001212454,"about_ca_system_score_gemma":0.00006548841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006580972,"about_ca_topic_score_gemma":0.00003074697,"domain_scores_codex":[0.9978177,0.00001915484,0.0006203704,0.0005631302,0.0005247604,0.000454914],"domain_scores_gemma":[0.9988832,0.0002046725,0.0003581661,0.0001928231,0.0002756607,0.00008551771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006459819,0.0003352977,0.005632865,0.0000783886,0.00008437847,0.00001366511,0.02493478,0.01713459,0.01041475,0.7175007,0.0000261639,0.2231984],"study_design_scores_gemma":[0.000116486,0.001810092,0.001731361,0.001143275,0.00001310687,0.00001908526,0.04205637,0.6934491,0.1873237,0.07160477,0.0001268623,0.0006057291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8837752,0.0000139331,0.08713484,0.001639473,0.0003163413,0.0007990789,0.000001844925,0.0001637794,0.02615547],"genre_scores_gemma":[0.9993362,0.00005818051,0.0001962907,0.00008306726,0.00002335013,0.00006622812,0.000001973085,0.0000147982,0.0002199372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6763145,"threshold_uncertainty_score":0.8932843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03813808714914614,"score_gpt":0.2861923081316865,"score_spread":0.2480542209825404,"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."}}