{"id":"W3037998275","doi":"10.65109/fyqq1225","title":"Inducing Cooperation through Reward Reshaping based on Peer Evaluations in Deep Multi-Agent Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Selfishness; Reinforcement learning; Computer science; Function (biology); Task (project management); Action (physics); Artificial intelligence; Dual (grammatical number); Action selection; Value (mathematics); Machine learning; Psychology; Social psychology; Engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0009165278,0.00020385,0.0001903282,0.0001422746,0.0002824168,0.0002987857,0.0005243205,0.00008615158,0.0001766307],"category_scores_gemma":[0.001473822,0.0002004604,0.00005902432,0.0007700015,0.00002444173,0.0007000843,0.0002137617,0.0005187457,0.0002553559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251518,"about_ca_system_score_gemma":0.0001543653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005819522,"about_ca_topic_score_gemma":0.00001478946,"domain_scores_codex":[0.997384,0.0002371682,0.0005478964,0.000523835,0.0009382867,0.0003687873],"domain_scores_gemma":[0.998897,0.0001727115,0.0001627015,0.0004077663,0.0002535151,0.0001062724],"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":[0.000008582948,0.0000183023,0.0007841267,0.00001401806,0.000006996485,0.000005405937,0.004148105,0.9889019,0.0004629289,0.004527057,0.0002658592,0.0008566959],"study_design_scores_gemma":[0.0009930742,0.0003017113,0.0004779584,0.00006837654,0.000005774195,4.54421e-7,0.0001989246,0.9937319,0.001389801,0.000008697166,0.002589498,0.0002338658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009745428,0.00001239688,0.9833703,0.007298609,0.0001764273,0.0004664493,8.171023e-8,0.0002691732,0.007432041],"genre_scores_gemma":[0.8611854,0.000004641131,0.1307989,0.006970316,0.00005302858,0.00003605801,0.00002496192,0.00001772954,0.0009090014],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8602108,"threshold_uncertainty_score":0.8174537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1017844746347217,"score_gpt":0.3330750631589225,"score_spread":0.2312905885242008,"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."}}