{"id":"W4410863960","doi":"10.1007/978-3-031-84756-1_10","title":"Reinforcement Learning PCG","year":2025,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on games and computational intelligence","topic":"Control and Dynamics of Mobile Robots","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Sudbury; University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00006721254,0.0003328506,0.0003154434,0.0001991224,0.00009161828,0.00007252232,0.0001503167,0.0001818624,0.0002910561],"category_scores_gemma":[0.00005390271,0.0003185991,0.0001273816,0.00002555588,0.00005434701,0.00002733202,0.00004511141,0.0003975478,0.00004834337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000692196,"about_ca_system_score_gemma":0.00003485162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004645923,"about_ca_topic_score_gemma":0.000006877273,"domain_scores_codex":[0.9990016,0.000009799833,0.0002952172,0.0002880704,0.0002307898,0.0001745672],"domain_scores_gemma":[0.9988633,0.0008166936,0.0000600483,0.0001317721,0.00006542046,0.00006279191],"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":[0.00001178991,0.000002378766,6.728515e-7,0.00006494114,0.00009677971,0.000003596772,0.00002070316,0.6995578,0.000001492864,0.08150358,0.0003692499,0.218367],"study_design_scores_gemma":[0.00003747405,0.00006609719,0.00002154573,0.0007304222,0.00005400558,0.000006042131,0.000007221036,0.8909909,0.00007790797,0.06802195,0.03957028,0.0004162116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00001814684,0.00410097,0.452195,0.0001838506,0.0002369643,0.0002629067,0.00001658346,0.0002593758,0.5427262],"genre_scores_gemma":[0.8287263,0.002955304,0.001086831,0.000412106,0.0001996099,0.00006635734,0.00006665281,0.00008298209,0.1664039],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8287082,"threshold_uncertainty_score":0.9999266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00784825310343568,"score_gpt":0.2111559141055218,"score_spread":0.2033076610020861,"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."}}