{"id":"W4409347970","doi":"10.1609/aaai.v39i22.34490","title":"Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Chinese Academy of Sciences","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006979383,0.0002061982,0.0002247945,0.0002453855,0.0002743616,0.0002321488,0.001414798,0.00007667908,0.00001284296],"category_scores_gemma":[0.0003549873,0.0001573007,0.00005648117,0.0009154552,0.0002002413,0.00009641932,0.0004603557,0.0004432002,0.00002322452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001561443,"about_ca_system_score_gemma":0.0001420617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008608641,"about_ca_topic_score_gemma":0.00002680638,"domain_scores_codex":[0.998159,0.00004453958,0.0006585265,0.0003934365,0.0004327311,0.0003118013],"domain_scores_gemma":[0.9984218,0.0001043187,0.0004415883,0.0004200065,0.0005679462,0.00004435964],"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":[0.00002515732,0.00005280114,0.0005653755,0.00002124643,0.000009961904,1.962007e-7,0.0008510516,0.6308149,0.01183799,0.3522922,0.00001920815,0.003509992],"study_design_scores_gemma":[0.000079284,0.0001366022,0.0004327121,0.0003401425,0.000008356497,0.000001294111,0.0004402229,0.8942902,0.1030955,0.0009873925,0.00004227172,0.0001459739],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1627973,0.00002522803,0.8249527,0.002727269,0.0001977134,0.0007723065,2.795475e-7,0.0000902107,0.00843704],"genre_scores_gemma":[0.9893023,0.00002382644,0.009770432,0.0001662302,0.00000886089,0.00004356061,0.000001031103,0.000007968785,0.0006757884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.826505,"threshold_uncertainty_score":0.6414535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08210690364603603,"score_gpt":0.3130108242529906,"score_spread":0.2309039206069546,"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."}}