{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00264237,0.000919382,0.0010888,0.0003471437,0.0004518937,0.0006988895,0.001669646,0.001116484,0.00115772],"category_scores_gemma":[0.006606227,0.0003990348,0.0003204767,0.0002243612,0.001300674,0.001123302,0.001814224,0.001402697,0.0002031881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001067229,"about_ca_system_score_gemma":0.001227528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002493918,"about_ca_topic_score_gemma":0.002947171,"domain_scores_codex":[0.9989789,0.0004505037,0.00004624808,0.0001840117,0.0001910464,0.0001494807],"domain_scores_gemma":[0.9973869,0.001340914,0.0003994347,0.0002036455,0.0003917448,0.0002773863],"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":[0.0001481795,0.0001558358,0.002067761,0.00006003385,0.00006259164,0.0001059498,0.0001773358,0.9273925,0.003493356,0.01346003,0.0009043543,0.05197201],"study_design_scores_gemma":[0.00001445611,0.00003945921,0.00008029201,0.000003910145,0.000005167853,0.00000977421,0.000007372588,0.9953803,0.0004300456,0.003863292,0.0001616975,0.00000430629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09008187,0.0002083682,0.9061229,0.0004582653,0.00005327913,0.00009611156,0.00001937289,0.0003462853,0.002613563],"genre_scores_gemma":[0.9428162,0.00005346326,0.05521856,0.0001487434,0.00001624202,0.0001114965,0.00002272325,0.00003354304,0.001578875],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00264237,"threshold_uncertainty_score":0.01397431,"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."}}