{"id":"W7076000553","doi":"","title":"Self-Play Q-Learners Can Provably Collude in the Iterated Prisoner's Dilemma","year":2025,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Simons Institute for the Theory of Computing, University of California Berkeley; Samsung; European Commission; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Dilemma; Iterated function; Class (philosophy); Key (lock); Face (sociological concept)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.009505186,0.0008143911,0.001052273,0.0006999075,0.002562193,0.003805989,0.001862122,0.003370778,0.01613547],"category_scores_gemma":[0.06092275,0.0005326596,0.0008915162,0.0004433552,0.005664689,0.00677248,0.005756159,0.003510187,0.001629462],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001014772,"about_ca_system_score_gemma":0.001956988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007221403,"about_ca_topic_score_gemma":0.0006239684,"domain_scores_codex":[0.9947624,0.003137202,0.0002316255,0.0006077468,0.0007054798,0.0005556847],"domain_scores_gemma":[0.9400442,0.04945829,0.002775332,0.002671846,0.002162295,0.002888023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005718928,0.0002671688,0.001875432,0.0001971662,0.00006286729,0.000718449,0.004374782,0.02373454,0.002093031,0.9443822,0.003088651,0.0186338],"study_design_scores_gemma":[0.00009644739,0.00009969845,0.0001300206,0.00002605092,0.00001149251,0.00008209368,0.0005111342,0.06687047,0.0004203224,0.930137,0.001597784,0.00001750261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4137797,0.0002843562,0.4960972,0.006028058,0.0003388624,0.000460166,0.0001016885,0.0007321531,0.0821778],"genre_scores_gemma":[0.9664247,0.00008391678,0.02221652,0.0003092733,0.00006259624,0.000231342,0.00002981355,0.00009777959,0.01054407],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01613547,"threshold_uncertainty_score":0.05397856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01405098361311395,"score_gpt":0.1967782516738354,"score_spread":0.1827272680607215,"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."}}