FA3C: FPGA-Accelerated Deep Reinforcement Learning
- Authors
- Cho, Hyungmin; H.; Oh; P.; Park; J.; Jung; W.; Lee; J.
- Issue Date
- 2019
- Publisher
- ASSOC COMPUTING MACHINERY
- Keywords
- reinforcement learning; deep neural networks; FPGA
- Citation
- International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS, pp.499 - 513
- Journal Title
- International Conference on Architectural Support for Programming Languages and Operating Systems - ASPLOS
- Start Page
- 499
- End Page
- 513
- URI
- https://scholarworks.bwise.kr/hongik/handle/2020.sw.hongik/12784
- DOI
- 10.1145/3297858.3304058
- ISSN
- 0000-0000
- Abstract
- Deep Reinforcement Learning (Deep RL) is applied to many areas where an agent learns how to interact with the environment to achieve a certain goal, such as video game plays and robot controls. Deep RL exploits a DNN to eliminate the need for handcrafted feature engineering that requires prior domain knowledge. The Asynchronous Advantage Actor-Critic (A3C) is one of the state-of-the-art Deep RL methods. In this paper, we present an FPGA-based A3C Deep RL platform, called FA3C. Traditionally, FPGA-based DNN accelerators have mainly focused on inference only by exploiting fixed-point arithmetic. Our platform targets both inference and training using single-precision floating-point arithmetic. We demonstrate the performance and energy efficiency of FA3C using multiple A3C agents that learn the control policies of six Atari 2600 games. Its performance is better than a high-end GPU-based platform (NVIDIA Tesla P100). FA3C achieves 27.9% better performance than that of a state-of-the-art GPU-based implementation. Moreover, the energy efficiency of FA3C is 1.62x better than that of the GPU-based implementation.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > Computer Engineering Major > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.