{"id":"W4402576032","doi":"10.2139/ssrn.4926191","title":"Game Theory and Multi-Agent Reinforcement Learning: A Mathematical Overview","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Economic theories and models","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Computer science; Game theory; Reinforcement; Artificial intelligence; Mathematical economics; Management science; Mathematics; Psychology; Economics; 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":[0.001483303,0.00131161,0.001697766,0.001141601,0.0005361399,0.002902941,0.00193199,0.00268798,0.003978234],"category_scores_gemma":[0.003652882,0.0006547705,0.001324134,0.002152849,0.002284208,0.003012229,0.001294953,0.003116466,0.0008862714],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001856887,"about_ca_system_score_gemma":0.001586747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004002834,"about_ca_topic_score_gemma":0.002141303,"domain_scores_codex":[0.9991509,0.000369466,0.00006575452,0.0001445523,0.0002101433,0.00005923781],"domain_scores_gemma":[0.9982686,0.001334151,0.0001323051,0.00006998034,0.0001396028,0.00005528799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001066588,0.00005301315,0.0003010227,0.0002499093,0.00004937417,0.00006820201,0.00006977917,0.1031481,0.0003440563,0.8751519,0.001888648,0.01866528],"study_design_scores_gemma":[0.0000129826,0.00002408688,0.0001951969,0.0000713772,0.00002034345,0.00008422539,0.00002524276,0.2385464,0.0001119076,0.752168,0.008719976,0.00002024629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004239248,0.02100549,0.94821,0.001987064,0.0001778565,0.00006282591,0.0001609428,0.00008423553,0.02407239],"genre_scores_gemma":[0.5502199,0.06593318,0.3541091,0.001465805,0.001978705,0.0007827949,0.0004729669,0.0001513482,0.0248863],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004002834,"threshold_uncertainty_score":0.0134728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03594363001411906,"score_gpt":0.259253789203876,"score_spread":0.2233101591897569,"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."}}