A3C-S: Automated Agent Accelerator Co-Search towards Efficient Deep Reinforcement Learning

Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications, there has been a growing demand to deploy DRL agents to empower daily-life intelligent devices, while the prohibitive complexity of DRL stands at odds...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2021 58th ACM/IEEE Design Automation Conference (DAC) s. 13 - 18
Hlavní autoři:	Fu, Yonggan, Zhang, Yongan, Li, Chaojian, Yu, Zhongzhi, Lin, Yingyan
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	IEEE 05.12.2021
Témata:	Accelerated aging AutoML Deep Reinforcement Learning Design automation DNA Knowledge engineering Life estimation Network Accelerator Co-design Reinforcement learning Training
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Driven by the explosive interest in applying deep reinforcement learning (DRL) agents to numerous real-time control and decision-making applications, there has been a growing demand to deploy DRL agents to empower daily-life intelligent devices, while the prohibitive complexity of DRL stands at odds with limited on-device resources. In this work, we propose an Automated Agent Accelerator Co-Search (A3C-S) framework, which to our best knowledge is the first to automatically co-search the optimally matched DRL agents and accelerators that maximize both test scores and hardware efficiency. Extensive experiments consistently validate the superiority of our A3C-S over state-of-the-art techniques.
DOI:	10.1109/DAC18074.2021.9586305