{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003086266,0.0007091577,0.0006305808,0.003419999,0.0004164442,0.0002045486,0.001262724,0.0003951825,0.001511065],"category_scores_gemma":[0.000885152,0.0006613578,0.0001205017,0.004968731,0.001049114,0.0004547801,0.0006095509,0.000978256,0.007947273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002935383,"about_ca_system_score_gemma":0.0008347424,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.007293837,"about_ca_topic_score_gemma":0.05661969,"domain_scores_codex":[0.9937748,0.0001725852,0.0009505498,0.001469649,0.002239126,0.001393258],"domain_scores_gemma":[0.9976615,0.0001291258,0.0008097158,0.0007809274,0.0002876074,0.0003311316],"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":[0.00002012119,0.0001960786,0.001262948,0.00005845807,0.00005042947,0.00003319473,0.0005394375,0.9763102,0.001007176,0.004650099,0.01142854,0.004443309],"study_design_scores_gemma":[0.001784611,0.0001667384,0.00100085,0.0003653767,0.0000401692,0.000002829978,0.001951214,0.9573545,0.00005473912,0.0001594909,0.03607996,0.001039556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.00896076,0.001546573,0.4555299,0.002600541,0.01627188,0.01328787,0.0002879216,0.02108249,0.4804321],"genre_scores_gemma":[0.6204444,0.00009948272,0.001947222,0.0001684118,0.0002859125,0.0001477672,0.000415368,0.002062694,0.3744288],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6114836,"threshold_uncertainty_score":0.9995838,"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."}}