{"id":"W2901559512","doi":"10.22215/etd/2013-09907","title":"Study of Multiple Multiagent Reinforcement Learning Algorithms in Grid Games","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Nash equilibrium; Minimax; Computer science; Algorithm; Best response; Grid; Game theory; Mathematical optimization; Artificial intelligence; Mathematics; Mathematical economics","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":[0.001933772,0.0006432664,0.001063213,0.0004329168,0.0004791656,0.001198177,0.00120425,0.0008433882,0.00235038],"category_scores_gemma":[0.009643539,0.0003523657,0.0005307882,0.000481705,0.001196716,0.001535091,0.0009031967,0.001271504,0.0001833778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001145094,"about_ca_system_score_gemma":0.001081244,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003683897,"about_ca_topic_score_gemma":0.001550812,"domain_scores_codex":[0.9991795,0.0004856605,0.00002815733,0.0000936673,0.0001356412,0.00007730232],"domain_scores_gemma":[0.9945602,0.004516179,0.0002893166,0.0001315333,0.0002840716,0.0002187787],"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":[0.0000474712,0.00005364013,0.0006747248,0.00007226045,0.00004552141,0.00005186625,0.0000755915,0.9039366,0.0002829516,0.08445425,0.0005664359,0.009738658],"study_design_scores_gemma":[0.00001226347,0.0000181611,0.00005209183,0.000006841816,0.00000293303,0.000006369889,0.00001039899,0.9826174,0.00006522935,0.0169331,0.0002729901,0.000002203881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1047011,0.001384903,0.8743282,0.001356978,0.0001347487,0.0001408273,0.00003732647,0.0001282895,0.01778759],"genre_scores_gemma":[0.9292274,0.0006476762,0.06477211,0.0001101058,0.00007541075,0.0001839452,0.00003417732,0.00005121047,0.004897865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003683897,"threshold_uncertainty_score":0.01022685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02480748313668581,"score_gpt":0.2822074256128413,"score_spread":0.2573999424761556,"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."}}