{"id":"W3201099806","doi":"10.1109/lra.2021.3139145","title":"Learning Selective Communication for Multi-Agent Path Finding","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"","keywords":"Computer science; Overhead (engineering); Imitation; Reinforcement learning; Artificial intelligence; Path (computing); Focus (optics); Simple (philosophy); Scheme (mathematics); Machine learning; Telecommunications network; Distributed computing; Computer network; Mathematics","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":[0.0002666481,0.0001144411,0.0001278275,0.00007345909,0.0003824841,0.0003063472,0.0002217097,0.00004879206,0.000001534599],"category_scores_gemma":[0.0001223029,0.0001253861,0.00004815109,0.0002128709,0.00002701747,0.0003437958,0.00008979734,0.0001693894,0.000008038716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007351528,"about_ca_system_score_gemma":0.00003764358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002857344,"about_ca_topic_score_gemma":0.000001299301,"domain_scores_codex":[0.9990408,0.000110443,0.0002324124,0.0002422999,0.0001674819,0.0002065715],"domain_scores_gemma":[0.9991868,0.0001913658,0.0001744325,0.0002670845,0.0001313751,0.00004893377],"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":[7.404927e-7,0.00001290733,0.000603686,0.00002674787,0.00002187888,0.000002112074,0.001102844,0.9854792,0.006003556,0.004177393,0.0003360714,0.002232865],"study_design_scores_gemma":[0.0003935696,0.00003426726,0.002591207,0.0000472734,0.00001177162,0.000007954215,0.00006132689,0.9941434,0.001978162,0.000051234,0.0005295276,0.0001503045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01003184,0.00004348516,0.9862332,0.00304775,0.0002517579,0.0001727735,5.389846e-7,0.000172321,0.00004628274],"genre_scores_gemma":[0.5175215,0.00004080142,0.4813157,0.0008299212,0.00002891185,0.00001664348,0.00002106718,0.00001182603,0.000213666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5074896,"threshold_uncertainty_score":0.5113097,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03388270364324859,"score_gpt":0.2801529579146556,"score_spread":0.246270254271407,"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."}}