{"id":"W4280563754","doi":"10.18196/jrc.v3i2.13082","title":"Consensus of Multi-agent Reinforcement Learning Systems: The Effect of Immediate Rewards","year":2022,"lang":"en","type":"article","venue":"Journal of Robotics and Control (JRC)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Cumulative prospect theory; Computer science; Function (biology); Artificial intelligence; Mathematics; Statistics","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":[0.002879297,0.0007890377,0.0009199568,0.0003404407,0.0004353296,0.0006973399,0.0007685035,0.0008028873,0.0007975047],"category_scores_gemma":[0.008835212,0.0002790345,0.0004317315,0.0001739613,0.00112174,0.001106039,0.001020599,0.0009905127,0.0000825613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008335281,"about_ca_system_score_gemma":0.000895902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002474153,"about_ca_topic_score_gemma":0.001349312,"domain_scores_codex":[0.9989293,0.0004836775,0.00004233703,0.0001782248,0.0001972402,0.000169151],"domain_scores_gemma":[0.9921964,0.005660563,0.0008337416,0.0002768709,0.0006462428,0.0003861412],"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":[0.00009545744,0.00003656709,0.0005771861,0.00004458989,0.0000322173,0.00008743758,0.00004683617,0.9858242,0.001396808,0.005227001,0.00009800385,0.006533733],"study_design_scores_gemma":[0.00001026224,0.00006553176,0.0001124937,0.000003216245,0.000005821602,0.00001025731,0.000009404567,0.9975778,0.0004552673,0.001688661,0.00005759129,0.000003736365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2142114,0.0004811933,0.78114,0.000378468,0.00006685637,0.00006224999,0.00001452159,0.000220399,0.003424858],"genre_scores_gemma":[0.9890843,0.00007044284,0.01025273,0.00002789467,0.00001281352,0.00001994839,0.000004560095,0.00001134083,0.000515987],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002879297,"threshold_uncertainty_score":0.01522732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01050280994847894,"score_gpt":0.233200328614998,"score_spread":0.2226975186665191,"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."}}