{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008114966,0.000222057,0.000202215,0.0002099878,0.0002153611,0.0009327492,0.0006946292,0.00008607998,0.00002306717],"category_scores_gemma":[0.0001346703,0.0001875044,0.0001512928,0.0003553194,0.00002811289,0.0005110207,0.0001847931,0.0002595381,0.0002506297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001912483,"about_ca_system_score_gemma":0.0001857647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002873822,"about_ca_topic_score_gemma":7.458688e-7,"domain_scores_codex":[0.9980032,0.00006750062,0.0004496199,0.0005257574,0.0004671211,0.0004867713],"domain_scores_gemma":[0.9989249,0.0002119967,0.00009100315,0.0005183549,0.0001283837,0.0001253857],"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":[0.000003747254,0.0000105784,0.00007298837,0.0003494443,0.00003517811,0.000008779937,0.0002192457,0.930145,0.00009138038,0.06610437,0.001943528,0.00101576],"study_design_scores_gemma":[0.0003461271,0.000235994,0.00001072653,0.0001422519,0.00001240722,0.000003612037,0.00003523868,0.859709,0.0004289035,0.00001510633,0.1388397,0.0002208848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00005368778,0.000281981,0.9924129,0.0004899597,0.001673311,0.001018281,4.023746e-7,0.001328345,0.002741093],"genre_scores_gemma":[0.6688645,0.00003442189,0.2671626,0.0004463646,0.0002097488,0.000444713,0.00003105266,0.0000591127,0.06274744],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7252504,"threshold_uncertainty_score":0.8994523,"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."}}