Presentation | 2021-10-28 Study on rounding error and Learning performance of reinforcement learning model for FPGA implementation Daisuke Oguchi, Satoshi Moriya, Hideaki Yamamoto, Shigeo Sato, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In recent years, the hardware implementation of reinforcement learning (RL) has attracted attention due to its wide range availability. We study a dedicated hardware architecture, which efficiently executes RL algorithm, and its realization in an FPGA. We investigated the learning performance when the bit-length was limited and found that the performance was maintained even when the bit-length was limited to 16, which results in saving circuit resources and power consumption. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Reinforcement Learning / FPGA / Q-learning / Edge Computing |
Paper # | NC2021-24 |
Date of Issue | 2021-10-21 (NC) |
Conference Information | |
Committee | MBE / NC |
---|---|
Conference Date | 2021/10/28(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Ryuhei Okuno(Setsunan Univ.) / Rieko Osu(Waseda Univ.) |
Vice Chair | Junichi Hori(Niigata Univ.) / Hiroshi Yamakawa(Univ of Tokyo) |
Secretary | Junichi Hori(Osaka Electro-Communication Univ) / Hiroshi Yamakawa(ATR) |
Assistant | Jun Akazawa(Meiji Univ. of Integrative Medicine) / Emi Yuda(Tohoku Univ) / Nobuhiko Wagatsuma(Toho Univ.) / Tomoki Kurikawa(KMU) |
Paper Information | |
Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Study on rounding error and Learning performance of reinforcement learning model for FPGA implementation |
Sub Title (in English) | |
Keyword(1) | Reinforcement Learning |
Keyword(2) | FPGA |
Keyword(3) | Q-learning |
Keyword(4) | Edge Computing |
1st Author's Name | Daisuke Oguchi |
1st Author's Affiliation | Tohoku University(Tohoku Univ) |
2nd Author's Name | Satoshi Moriya |
2nd Author's Affiliation | Tohoku University(Tohoku Univ) |
3rd Author's Name | Hideaki Yamamoto |
3rd Author's Affiliation | Tohoku University(Tohoku Univ) |
4th Author's Name | Shigeo Sato |
4th Author's Affiliation | Tohoku University(Tohoku Univ) |
Date | 2021-10-28 |
Paper # | NC2021-24 |
Volume (vol) | vol.121 |
Number (no) | NC-223 |
Page | pp.pp.34-39(NC), |
#Pages | 6 |
Date of Issue | 2021-10-21 (NC) |