{"id":"W4205522428","doi":"10.1109/icrae53653.2021.9657767","title":"Deep Reinforcement Learning for Flocking Control of UAVs in Complex Environments","year":2021,"lang":"en","type":"article","venue":"","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Flocking (texture); Reinforcement learning; Computer science; Markov decision process; Kinematics; Partially observable Markov decision process; Collision; Swarm behaviour; Artificial intelligence; Distributed computing; Markov process; Markov chain; Machine learning; Markov model; 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":[0.0003337936,0.0001215015,0.00029175,0.00006720884,0.00005576882,0.00005622825,0.0004058405,0.00004593618,0.00005748217],"category_scores_gemma":[0.00009551794,0.0001230599,0.00009182416,0.000165553,0.00001701128,0.0001909754,0.0001348421,0.00007826449,0.00001775461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009613793,"about_ca_system_score_gemma":0.00003418885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000395081,"about_ca_topic_score_gemma":0.00002590737,"domain_scores_codex":[0.9985141,0.00009732737,0.0004793336,0.0003154122,0.0002785831,0.000315225],"domain_scores_gemma":[0.9992037,0.0001676766,0.0001639087,0.0003604377,0.00004467115,0.00005957699],"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":[0.00003366311,0.000166217,0.009755175,0.00007350859,0.0001256191,0.00002883802,0.000591669,0.8657517,0.06714953,0.03996365,0.0001298788,0.01623055],"study_design_scores_gemma":[0.00300613,0.00005590648,0.003606266,0.00002212065,0.000006891808,0.000003050243,0.0001136801,0.9819168,0.003622726,0.00007317649,0.007446517,0.0001267048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001576865,0.00008959481,0.9959167,0.0002410868,0.0001160438,0.0003926808,0.0000011512,0.00003441457,0.001631449],"genre_scores_gemma":[0.9925293,0.000003914886,0.006573339,0.0001708291,0.00002147758,0.00005980734,0.00002788531,0.00000733559,0.0006061295],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9909524,"threshold_uncertainty_score":0.5018239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02372252897729252,"score_gpt":0.2439857517237118,"score_spread":0.2202632227464193,"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."}}