Authors: M. Rothmann and M. Porrmann
Date: 26 January 2022
DOI Bookmark: 10.1109/ACCESS.2022.3146518
Supported by VEDLIoT, a new survey of domain-specific architectures for reinforcement learning is now available through IEEEXplore.
Reinforcement learning algorithms have been very successful at solving sequential decision-making problems in many different problem domains. However, their training is often time-consuming, with training times ranging from multiple hours to weeks. The development of domain-specific architectures for reinforcement learning promises faster computation times, decreased experiment turn-around time, and improved energy efficiency. This paper presents a review of hardware architectures for the acceleration of reinforcement learning algorithms. FPGA-based implementations are the focus of this work, but GPU-based approaches are considered as well.
In addition to an in-depth analysis of the state-of-the art, directions for future research are discussed. The survey will serve as an important basis for the accelerator developments in VEDLIoT.
View the fully open access article here.