{"id":"W4399729340","doi":"10.1109/syscon61195.2024.10553598","title":"Deep Reinforcement Learning Agents for Decision Making for Gameplay","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Human–computer interaction; Artificial intelligence; Reinforcement; Psychology; Social psychology","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":[0.0007462185,0.0007556371,0.0005751279,0.0003068981,0.0003794231,0.0009562155,0.001395579,0.001007266,0.005567947],"category_scores_gemma":[0.002519439,0.0004183278,0.0004787733,0.0002339535,0.0008102387,0.0009625591,0.000931014,0.002133706,0.0009358534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001294676,"about_ca_system_score_gemma":0.001275143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008080744,"about_ca_topic_score_gemma":0.01152484,"domain_scores_codex":[0.9997157,0.00009301788,0.00001759243,0.00005112879,0.00007439891,0.00004803738],"domain_scores_gemma":[0.9992523,0.0004392355,0.00006519643,0.00005028217,0.0001350563,0.00005799023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009429426,0.0001194974,0.0006807399,0.00008819301,0.00004554575,0.00006925453,0.0000824087,0.8824015,0.002380399,0.02922462,0.002426486,0.08238713],"study_design_scores_gemma":[0.000008911082,0.00001498015,0.00004629064,0.000006529256,0.000003603086,0.000005791263,0.000004700063,0.9913706,0.0003936906,0.00709213,0.00104927,0.000003545229],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01747018,0.0006050787,0.9706739,0.0005434862,0.00008820848,0.0001023838,0.00008114058,0.001332791,0.009102896],"genre_scores_gemma":[0.7446314,0.0004873571,0.2424024,0.0003342805,0.00005089967,0.0003372252,0.0001688843,0.0001395417,0.0114481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008080744,"threshold_uncertainty_score":0.01862663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03155200176925009,"score_gpt":0.3237776472711069,"score_spread":0.2922256455018568,"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."}}