{"id":"W4387394771","doi":"10.1609/aiide.v19i1.27522","title":"Mechanic Maker 2.0: Reinforcement Learning for Evaluating Generated Rules","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":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"USable; Reinforcement learning; Computer science; Artificial intelligence; Meaning (existential); Reinforcement; Machine learning; Human–computer interaction; Psychology; Multimedia; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005987231,0.0003197519,0.0003119543,0.0002292798,0.0003262943,0.0007852196,0.00102148,0.00007839338,0.00003845767],"category_scores_gemma":[0.0009816274,0.0002445464,0.0001872001,0.0004778106,0.0001665203,0.001093552,0.0006899337,0.0002743143,0.0001314571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109904,"about_ca_system_score_gemma":0.00005715424,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000146165,"about_ca_topic_score_gemma":0.000002195353,"domain_scores_codex":[0.9974833,0.00002317875,0.0007527495,0.0006572337,0.0005780786,0.0005055287],"domain_scores_gemma":[0.9980919,0.0003109942,0.000480948,0.000225005,0.0007845642,0.0001066227],"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":[0.0002760991,0.0001669729,0.0001842892,0.00007506643,0.0001091685,0.000001028161,0.004922161,0.002880764,0.05744639,0.5487095,0.0002161196,0.3850125],"study_design_scores_gemma":[0.00003543938,0.0006795092,0.00003403619,0.0002698187,0.0000117163,0.000002683507,0.002951009,0.5432798,0.3850289,0.06727999,0.0002082921,0.0002187248],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7006357,0.00002287909,0.2856296,0.003647822,0.0009089736,0.001853203,0.00001587486,0.0003079676,0.00697791],"genre_scores_gemma":[0.9976332,0.00004748665,0.0006697833,0.0001919036,0.00005436645,0.0001905936,0.000007671351,0.00002184062,0.001183107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5403991,"threshold_uncertainty_score":0.9972311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09860666841973242,"score_gpt":0.3392778733725346,"score_spread":0.2406712049528021,"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."}}