{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004065195,0.001069419,0.0008274899,0.000986825,0.0003180447,0.001352989,0.002849967,0.00154707,0.009095776],"category_scores_gemma":[0.01406147,0.0007083133,0.0004953381,0.0003754323,0.000945388,0.001470756,0.001514065,0.001861019,0.001802632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009321203,"about_ca_system_score_gemma":0.001599878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002487641,"about_ca_topic_score_gemma":0.004060734,"domain_scores_codex":[0.9986122,0.0005542733,0.00009147808,0.0002750019,0.0003634469,0.0001037238],"domain_scores_gemma":[0.994293,0.004348513,0.0003132847,0.0004993664,0.0003902971,0.0001555305],"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":[0.001203707,0.0007873575,0.00680699,0.0009583547,0.0001949844,0.0002885083,0.000367784,0.5446818,0.01298644,0.0352772,0.01576629,0.3806805],"study_design_scores_gemma":[0.00006147015,0.00007047332,0.0001845763,0.00001540111,0.000009482195,0.00002986664,0.000007808445,0.9897029,0.004571822,0.003715325,0.001620436,0.00001042479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0394063,0.0002860564,0.9068215,0.0002163558,0.0001126526,0.0004846984,0.0005100701,0.04500706,0.00715534],"genre_scores_gemma":[0.3637702,0.0001268224,0.6296507,0.0002311986,0.00002678811,0.0005829648,0.0005638704,0.001744747,0.003302689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009095776,"threshold_uncertainty_score":0.03042847,"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."}}