8 天前 - … an innovative trajectoryplanning algorithm for stratospheric airships, combining Artificial Potential Field (APF) method with Soft Actor-Critic (SAC) deep reinforcementlearning …
J Pan, Y Li, R Chai, S Xia, L Zuo - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
9 天前 - … trajectoryplanning and resource allocation scheme based on hierarchical deep reinforcementlearning … sub-problems: high-level global trajectoryplanning and low-level local …
A Plissonneau, L Jourdan, D Trentesaux, L Abdi… - … Rail Transport Planning …, 2024 - Elsevier
9 天前 - … consists of a deep reinforcementlearning (DRL) based … a method for training a reinforcementlearning (RL) agent … to be predictive of obstacle trajectories. A comparison study …
W Junyang, J Yibing, Z Jingdong, D Haowen… - me336.ancorasir.com
10 天前 - … RoboGen simultaneously employs motion planningbased primitives, gradient-based trajectory optimization, and reinforcementlearning to acquire skills. For each task, we …
RI Cabral Muchacho, FT Pokorny - arXiv e-prints, 2024 - ui.adsabs.harvard.edu
11 天前 - … to time-varying semantic information, and to perform queries in sub-microsecond, enabling applications in reinforcementlearning, trajectory optimization, and motion planning. …
T Liu, R Chai, S Chai, F Arvin, J Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
13 天前 - … , various trajectoryplanning … reinforcementlearning algorithm based on an end-to-end mapless collision avoidance algorithm for training in the proposed distributed learning …
13 天前 - … to generate intelligent planned behavior. Although reinforcementlearning methods that … gap by developing algorithms that compute trajectories in real-time while converging …
S Vakili, F Nabiei, D Shiu, A Bernacchia - … on Machine Learning - openreview.net
13 天前 - … This assumption simplifies the problem compared to the rewardfree RL framework considered in this work, where the agent must follow the MDP trajectory within each episode …
14 天前 - … to adapt to time-varying semantic information, and to perform queries in ≤ 1 µs, enabling applications in reinforcementlearning, trajectory optimization, and motion planning. …