{"id":"W4399376477","doi":"10.1109/iciprob62548.2024.10543232","title":"Proximity-Based Reward Systems for Multi-Agent Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Swarm behaviour; Artificial intelligence; Swarm intelligence; Swarm robotics; Machine learning; Euclidean distance; Robot; Particle swarm optimization","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002727326,0.0008197614,0.00101605,0.0005644181,0.0005983619,0.0009271747,0.001222099,0.0009064132,0.002175368],"category_scores_gemma":[0.01082851,0.0002643711,0.0003797554,0.0004514031,0.001047735,0.0014326,0.001373803,0.001565196,0.0002993657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542505,"about_ca_system_score_gemma":0.0008310059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002625044,"about_ca_topic_score_gemma":0.002123187,"domain_scores_codex":[0.9985529,0.0006646611,0.0001096872,0.0002406632,0.0003387228,0.0000934432],"domain_scores_gemma":[0.994802,0.003385017,0.0005665705,0.0002748423,0.0007254699,0.0002461327],"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":[0.0001120737,0.00009312505,0.0006938706,0.00007738428,0.00003227281,0.00003422356,0.00006537685,0.9435049,0.001055146,0.01489726,0.000378732,0.03905565],"study_design_scores_gemma":[0.00001423692,0.00007602631,0.0001059386,0.000007143314,0.000005370159,0.00001286777,0.000005964929,0.9940612,0.000421506,0.004967607,0.0003152931,0.000006973948],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03172497,0.0004811333,0.9648021,0.0002343661,0.00006245183,0.0001144643,0.00003108308,0.0003854312,0.00216407],"genre_scores_gemma":[0.8770816,0.000184327,0.1208506,0.0001035305,0.0000336192,0.0001908479,0.00004524086,0.00004124227,0.001468902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002727326,"threshold_uncertainty_score":0.01442367,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05601974589692608,"score_gpt":0.2998856358830855,"score_spread":0.2438658899861595,"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."}}