Journal
IEEE WIRELESS COMMUNICATIONS LETTERS
Volume 10, Issue 3, Pages 512-516Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LWC.2020.3036094
Keywords
Resource management; Power control; Receivers; Transmitters; Signal to noise ratio; Wireless communication; Reinforcement learning; Deep reinforcement learning; power control; interference channel; offline learning
Categories
Funding
- Huawei Canada Company Ltd.
Ask authors/readers for more resources
This study discusses how to accelerate the learning of power control in an unexplored environment using historical power control data, and introduces an offline deep reinforcement learning algorithm mBCQ, which increases learning speed by almost 50 times compared to conventional algorithms and demonstrates robustness to hyperparameters.
We address how to exploit historical power control data, gathered from a monitored environment, for accelerating the learning of power control in an unexplored environment when only partial channel state information, e.g., path-loss, is available. We adopt offline deep reinforcement learning (DRL), whereby the agent learns the policy to produce the transmission powers by using the historical data and occasional exploration and develops a new algorithm called modified batched constrained Q-learning (mBCQ). Compared to conventional continuous DRL algorithms, mBCQ increases the learning speed by almost 50 times and demonstrate robustness to hyper-parameters.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available