{"id":"W3093099641","doi":"10.22215/etd/2017-11788","title":"On Multi-Agent Reinforcement Learning in Matrix, Stochastic and Differential Games","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Guidance and Control Systems","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; Dalhousie University","funders":"","keywords":"Nash equilibrium; Reinforcement learning; Best response; Computer science; Convergence (economics); Mathematical optimization; Epsilon-equilibrium; Pursuer; Solution concept; Mathematics; Algorithm; Mathematical economics; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.00004800422,0.0002196373,0.0002928964,0.0001281014,0.00005640668,0.00008439931,0.00009487929,0.0001513497,0.00008346953],"category_scores_gemma":[0.00002604691,0.0001998518,0.0000470652,0.00001595335,0.000004959702,0.00004459183,0.000006375119,0.0002613893,0.00004655103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005341792,"about_ca_system_score_gemma":0.00001090422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001396317,"about_ca_topic_score_gemma":0.000570677,"domain_scores_codex":[0.9992327,0.00001057603,0.0002460212,0.0001713639,0.0001443736,0.0001949456],"domain_scores_gemma":[0.9996917,0.0000222039,0.0000695685,0.0001602698,0.00001402744,0.00004223884],"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":[0.0001709579,0.00004543086,0.0003319079,0.001313702,0.0002433644,0.00002662237,0.002612506,0.954574,0.006524383,0.001092762,0.0005374356,0.03252688],"study_design_scores_gemma":[0.003243172,0.0001578332,0.02951744,0.001622343,0.00008286886,0.000002115781,0.00108679,0.9622725,0.0004165074,0.00003987754,0.0007152461,0.0008433452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9507143,0.0016633,0.01777379,0.00000933609,0.002572338,0.0009752223,0.000002837973,0.0003391102,0.02594979],"genre_scores_gemma":[0.9521567,0.00005732303,0.000007928647,0.000002507655,0.00006945858,0.00008477266,0.0001054852,0.00003413265,0.0474817],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03168353,"threshold_uncertainty_score":0.8149719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009605333763256119,"score_gpt":0.2504946084800244,"score_spread":0.2408892747167683,"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."}}