Title
Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks
Abstract
In this paper, the design of an optimal trajectory for an energy-constrained drone operating in dynamic network environments is studied. In the considered model, a drone base station (DBS) is dispatched to provide uplink connectivity to ground users whose demand is dynamic and unpredictable. In this case, the DBS's trajectory must be adaptively adjusted to satisfy the dynamic user access requests. To this end, a metalearning algorithm is proposed in order to adapt the DBS's trajectory when it encounters novel environments, by tuning a reinforcement learning (RL) solution. The meta-learning algorithm provides a solution that adapts the DBS in novel environments quickly based on limited former experiences. The meta-tuned RL is shown to yield a faster convergence to the optimal coverage in unseen environments with a considerably low computation complexity, compared to the baseline policy gradient algorithm. Simulation results show that, the proposed meta-learning solution yields a 25% improvement in the convergence speed, and about 10% improvement in the DBS' communication performance, compared to a baseline policy gradient algorithm. Meanwhile, the probability that the DBS serves over 50% of user requests increases about 27%, compared to the baseline policy gradient algorithm.
Year
DOI
Venue
2020
10.1109/GLOBECOM42002.2020.9322414
GLOBECOM 2020 - 2020 IEEE Global Communications Conference
Keywords
DocType
ISSN
metalearning algorithm,reinforcement learning solution,meta-tuned RL,optimal coverage,unseen environments,computation complexity,baseline policy gradient algorithm,meta-learning solution,DBS communication performance,user requests,meta-reinforcement learning,trajectory design,wireless UAV networks,optimal trajectory,energy-constrained drone,dynamic network environments,drone base station,uplink connectivity,ground users whose demand,dynamic user access requests,DBS trajectory
Conference
1930-529X
ISBN
Citations 
PageRank 
978-1-7281-8299-5
1
0.35
References 
Authors
0
5
Name
Order
Citations
PageRank
Hu Ye110.35
Mingzhe Chen259544.32
Walid Saad34450279.64
H. V. Poor4254111951.66
Shuguang Cui552154.46