Title:
方法及び装置
Document Type and Number:
Japanese Patent JP7279856
Kind Code:
B2
Abstract:
We apply the techniques of deep reinforcement learning (RL) to the problem of coverage and capacity optimisation (CCO) in wireless networks. This is motivated by the idea that the type of combinatorial optimisation problems encountered in wireless networks are somewhat analogous to strategy games, for which deep RL has already proven to be an effective approach. We use a computer simulation of a small wireless network to generate synthetic data to train a deep Q network (DQN), and evaluate the performance of the DQN with further simulations. We compare the performance of the DQN with a conventional model-based approach. The results show that the DQN achieves slightly better performance than the conventional method, without the need for an explicit model of the environment. The performance is shown to be further improved by using the DQN within a search algorithm.
Inventors:
Arnot Robert
Swales Alberto
Wells Patricia
Swales Alberto
Wells Patricia
Application Number:
JP2022522498A
Publication Date:
May 23, 2023
Filing Date:
August 27, 2020
Export Citation:
Assignee:
NEC
International Classes:
H04W24/02; G06N3/08
Foreign References:
| US20190014488 |
Other References:
Alessio Zappone, et al.,Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both?,arxiv.org, Cornell Uiversity library,2019年06月13日
Ron Sun,Supplementing Neural Reinforcement Learning with Symbolic Methods: Possibilities and Challenges,IEEE,1999年07月10日
Ron Sun,Supplementing Neural Reinforcement Learning with Symbolic Methods: Possibilities and Challenges,IEEE,1999年07月10日
Attorney, Agent or Firm:
Ken Ieiri