{"id":"W3181415617","doi":"10.1109/itsc48978.2021.9564459","title":"Distributed Deep Reinforcement Learning for Intelligent Traffic Monitoring with a Team of Aerial Robots","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Vehicular Ad Hoc Networks (VANETs)","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Robot; Reinforcement learning; Computer science; Partially observable Markov decision process; Scalability; Distributed computing; Real-time computing; Markov decision process; Metric (unit); Network topology; Artificial intelligence; Markov process; Markov chain; Machine learning; Computer network; Engineering; Markov model","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":[0.0007383244,0.0008040948,0.0009296935,0.000269722,0.0004153932,0.0004863107,0.00122522,0.0008928137,0.001186911],"category_scores_gemma":[0.001900453,0.0003825041,0.0003507976,0.0002564388,0.0007435466,0.0006925569,0.001037198,0.001118626,0.0001586642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040512,"about_ca_system_score_gemma":0.001193193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009347735,"about_ca_topic_score_gemma":0.006998366,"domain_scores_codex":[0.9996811,0.00007898645,0.0000139351,0.00009167921,0.00005398884,0.00008030256],"domain_scores_gemma":[0.9991148,0.0004543156,0.0001542263,0.0000557395,0.0001230803,0.00009783352],"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":[0.0000614969,0.00005297589,0.0007612666,0.00002219933,0.00002074866,0.00005462089,0.0000371048,0.9739727,0.0008965159,0.001398758,0.0003713803,0.02235012],"study_design_scores_gemma":[0.000004980348,0.00001195967,0.00003541716,9.209274e-7,0.000001592933,0.000002588148,0.000002938711,0.9993916,0.00009149423,0.0004129677,0.00004278085,8.415196e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1101704,0.0003551458,0.8855324,0.0004012354,0.00006704548,0.000058144,0.00003645359,0.0008396882,0.002539468],"genre_scores_gemma":[0.9618172,0.00004902914,0.03702436,0.00006796345,0.0000165287,0.00004946526,0.00004148259,0.0000185354,0.0009155007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009347735,"threshold_uncertainty_score":0.01858664,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01339397099381632,"score_gpt":0.2283627373850887,"score_spread":0.2149687663912724,"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."}}