{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002461618,0.0008242143,0.001081067,0.0004316243,0.0007252611,0.0006911317,0.002214879,0.001103066,0.0008830308],"category_scores_gemma":[0.007728789,0.0004053923,0.0003118781,0.000413286,0.001182261,0.001515294,0.002219674,0.001481509,0.000199261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007447994,"about_ca_system_score_gemma":0.001330259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002601138,"about_ca_topic_score_gemma":0.002015983,"domain_scores_codex":[0.9985381,0.0005896168,0.00007676424,0.0002444542,0.0003847455,0.0001662949],"domain_scores_gemma":[0.9954965,0.002635862,0.0006254495,0.0004804256,0.0005382965,0.0002234597],"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":[0.0001799338,0.0001026141,0.0006485946,0.00005416479,0.00002457524,0.00009752684,0.000181178,0.9308138,0.002364674,0.008360893,0.000497219,0.05667472],"study_design_scores_gemma":[0.00002216629,0.00003017429,0.00003975109,0.000002005267,0.000002690672,0.000008850157,0.000006231206,0.9968069,0.0005097864,0.002442102,0.0001262172,0.000003234949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05137446,0.000122461,0.9463834,0.0001985155,0.00002764463,0.00006197063,0.00001266238,0.0004044509,0.001414536],"genre_scores_gemma":[0.9314519,0.00004202844,0.06709504,0.00008223066,0.00002347096,0.0001265742,0.00003146605,0.00003465775,0.001112733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002601138,"threshold_uncertainty_score":0.01301843,"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."}}