{"id":"W3142824457","doi":"10.1142/s2737480721500059","title":"Path Following Control for UAV Using Deep Reinforcement Learning Approach","year":2021,"lang":"en","type":"article","venue":"Guidance Navigation and Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Computer science; Path (computing); Convergence (economics); Motion planning; Function (biology); Artificial intelligence; Control (management); Trajectory; Q-learning; Action (physics); Domain (mathematical analysis); Mathematical optimization; Algorithm; Control theory (sociology); Mathematics; Robot","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":[0.0006322405,0.0001961099,0.0003052584,0.00005060954,0.0004404229,0.0003500884,0.0002677809,0.000091115,0.000004189832],"category_scores_gemma":[0.0002508851,0.0002022427,0.0001511023,0.0002348167,0.00002892079,0.0005051638,0.00006777137,0.0001975309,0.000004162292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008349238,"about_ca_system_score_gemma":0.0001075691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006756693,"about_ca_topic_score_gemma":1.763428e-7,"domain_scores_codex":[0.9982008,0.0001299287,0.0004519654,0.0004480266,0.0003697863,0.0003994995],"domain_scores_gemma":[0.9988798,0.000185011,0.0002563082,0.0003285847,0.0002406252,0.0001096895],"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":[0.00001735072,0.00001253465,0.002607439,0.00005605236,0.00007421395,0.000008429655,0.0003591731,0.9762392,0.005622292,0.01106612,0.00001429992,0.003922899],"study_design_scores_gemma":[0.003766521,0.00008369336,0.0002814115,0.00008152243,0.00005169453,0.00001623382,0.0001253796,0.9934425,0.0004122112,0.000189684,0.001315655,0.0002334448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004908539,0.0005948928,0.9927709,0.0002427442,0.000306629,0.0005090731,6.862822e-7,0.0001304402,0.0005361277],"genre_scores_gemma":[0.9407291,0.000008898717,0.05788505,0.0007759301,0.0001036821,0.00007792164,0.00002426529,0.00001643869,0.0003786866],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9358206,"threshold_uncertainty_score":0.8247218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01636363102140439,"score_gpt":0.2588017157053313,"score_spread":0.2424380846839269,"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."}}