Flexible chip placement via reinforcement learning: late breaking results.
Fu-Chieh ChangYu-Wei TsengYa-Wen YuSsu-Rui LeeAlexandru CiobaI-Lun TsengDa-Shan ShiuJhih-Wei HsuCheng-Yuan WangChien-Yi YangRen-Chu WangYao-Wen ChangTai-Chen ChenTung-Chieh ChenPublished in: DAC (2022)
Keyphrases
- reinforcement learning
- high speed
- modular design
- low cost
- function approximation
- learning algorithm
- lightweight
- multi agent
- programmable logic
- state space
- learning process
- low power
- high density
- circuit design
- machine learning
- robotic control
- vlsi design
- vlsi implementation
- reinforcement learning algorithms
- temporal difference
- action selection
- highly efficient