Journal
IEEE ACCESS
Volume 10, Issue -, Pages 13753-13767Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3146518
Keywords
Reinforcement learning; Computer architecture; Training; Neural networks; Optimization; Graphics processing units; Q-learning; Domain-specific architectures; machine learning; deep learning; reinforcement learning; deep reinforcement learning; reconfigurable architectures; FPGA
Categories
Funding
- European Union's Horizon 2020 Research and Innovation Program through the Very Efficient Deep Learning in IoT (VEDLIoT) Project [957197]
Ask authors/readers for more resources
This paper presents a review of hardware architectures for accelerating reinforcement learning algorithms, focusing on FPGA-based implementations and considering GPU-based approaches as well. It compares the techniques employed in different implementations and suggests possible areas for future work.
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. Both tabular and deep reinforcement learning algorithms are included in this survey. The techniques employed in different implementations are highlighted and compared. Finally, possible areas for future work are suggested, based on the preceding discussion of existing architectures.
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