{"id":"W2952370515","doi":"","title":"Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Evolutionary Game Theory and Cooperation","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Counterfactual thinking; Computer science; Social dilemma; Dilemma; Mechanism (biology); Social learning; Artificial intelligence; Reinforcement; Psychology; Knowledge management; 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":[0.002246442,0.0006797324,0.0007781357,0.0004503916,0.0006198863,0.00132438,0.001366528,0.00127912,0.002142703],"category_scores_gemma":[0.01187693,0.0003678374,0.0004743085,0.000285659,0.002123985,0.001866714,0.001956999,0.001759547,0.0001947862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001314721,"about_ca_system_score_gemma":0.001173411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001473839,"about_ca_topic_score_gemma":0.001839351,"domain_scores_codex":[0.9989191,0.0005391295,0.00004369434,0.0001830263,0.0001881251,0.0001268945],"domain_scores_gemma":[0.9952323,0.002691161,0.0008444038,0.0004193357,0.0003519706,0.0004608299],"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":[0.0001365149,0.0001762157,0.004353988,0.0001579512,0.0001455668,0.0002809982,0.0004551213,0.6266857,0.005376217,0.3273239,0.001499715,0.03340803],"study_design_scores_gemma":[0.00001555772,0.00003714541,0.0002228997,0.000008254564,0.00001056397,0.00002026566,0.00001764928,0.9302199,0.000349839,0.06862243,0.0004668862,0.000008626504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1298463,0.0002245571,0.8586704,0.001442989,0.00007565145,0.00007645959,0.00004842006,0.0002532382,0.009362056],"genre_scores_gemma":[0.9639214,0.00008494884,0.03406616,0.0001335665,0.00003116022,0.00008725278,0.00001972597,0.00003131681,0.001624434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002246442,"threshold_uncertainty_score":0.01188046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1057084921767029,"score_gpt":0.2582526959228985,"score_spread":0.1525442037461955,"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."}}