{"id":"W4231805100","doi":"10.22215/etd/2012-09679","title":"Multi-agent reinforcement learning in games","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Reinforcement learning; Humanities; Computer science; Artificial intelligence; Art","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":[0.001226481,0.0007384324,0.0008412668,0.0003320141,0.0003583181,0.0009984319,0.000936691,0.0007853429,0.002483099],"category_scores_gemma":[0.00390319,0.0003441648,0.0004311775,0.0003120554,0.0008726701,0.0009966898,0.0009838027,0.001484557,0.0003424532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386226,"about_ca_system_score_gemma":0.001143443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004888896,"about_ca_topic_score_gemma":0.004324891,"domain_scores_codex":[0.9991639,0.0005210757,0.00003365715,0.00009418644,0.0001061021,0.0000811065],"domain_scores_gemma":[0.9982238,0.001289097,0.0001014802,0.00007536467,0.0001438416,0.0001663144],"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":[0.0001177092,0.0001408444,0.0004703045,0.0001170371,0.00006506647,0.0000649794,0.0001155153,0.8589709,0.0008009883,0.09691387,0.002555333,0.03966751],"study_design_scores_gemma":[0.00003492628,0.00003544775,0.00006995673,0.000009351034,0.000004789542,0.000005686865,0.00001041465,0.9673579,0.0001477872,0.03105068,0.001268877,0.000004087144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03925319,0.001482885,0.9426865,0.001299297,0.0001564198,0.0001219708,0.00005286418,0.0002765788,0.0146703],"genre_scores_gemma":[0.8723326,0.001006092,0.1102357,0.0001758899,0.0001286118,0.0003342522,0.00008434528,0.00006549875,0.01563713],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004888896,"threshold_uncertainty_score":0.01005781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02646687385412405,"score_gpt":0.2866958448495736,"score_spread":0.2602289709954496,"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."}}