{"id":"W6966869692","doi":"10.48448/y8eb-h483","title":"Unequal Norms Emerge Under Coordination Uncertainty in Multi-Agent Deep Reinforcement Learning","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Outcome (game theory); Social dilemma; Reinforcement learning; Dilemma; Disadvantage; Population; Norm (philosophy)","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":[0.002215366,0.0004587614,0.000561899,0.0002708459,0.0004287407,0.001055342,0.0008007368,0.0008523409,0.001292845],"category_scores_gemma":[0.01251917,0.0003279083,0.0002381604,0.0001499948,0.00150221,0.0013959,0.001650213,0.001467864,0.0001273233],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009751892,"about_ca_system_score_gemma":0.0008407651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003426037,"about_ca_topic_score_gemma":0.003060555,"domain_scores_codex":[0.9992066,0.0003478482,0.00003273322,0.000172458,0.0001227925,0.0001175542],"domain_scores_gemma":[0.9962281,0.002021285,0.0007947899,0.0003046812,0.000257444,0.0003937979],"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":[0.0003065359,0.0001129981,0.01322905,0.00008102912,0.00009898456,0.0002676164,0.0003114857,0.8800765,0.004880769,0.06416763,0.001845606,0.03462175],"study_design_scores_gemma":[0.00001373593,0.00002268451,0.0007008265,0.000005279879,0.000005112083,0.00001188608,0.00001901089,0.9732497,0.0004576147,0.02532658,0.0001822133,0.000005247907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6877456,0.0002204041,0.3032107,0.00169265,0.00006596836,0.00003740627,0.0001233568,0.0003615563,0.006542342],"genre_scores_gemma":[0.9906894,0.00003247494,0.008124496,0.0001078196,0.00000976006,0.00002294989,0.00003195876,0.00002169115,0.0009593915],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003426037,"threshold_uncertainty_score":0.01171613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04908365477129078,"score_gpt":0.3312138761663124,"score_spread":0.2821302213950216,"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."}}