.png){kind=icon}
Return
A Deep Reinforcement Learning Framework for High-Dimensional Circuit Linearization
.png){kind=icon}
OA
AI
DOI：10.1109/TCSII.2022.3183156.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Despite the successes of Reinforcement Learning (RL) in recent years, tasks that require exploring over long trajectories with limited feedback and searching in high-dimensional space remain challenging. This brief proposes a deep RL framework for high-dimensional circuit linearization with an efficient exploration strategy leveraging a scaled dot-product attention scheme and search on the replay technique. As a proof of concept, a 5-bit digital-to-time converter (DTC) is built as the environment, and an RL agent learns to tune the calibration words of the delay stages to minimize the integral nonlinearity (INL) with only scalar feedback. The policy network which selects calibration words is trained by the Soft Actor-Critic (SAC) algorithm. Our results show that the proposed RL framework can reduce the INL to less than 0.5 LSB within 60, 000 trials, which is much smaller than the size of searching space.
Keywords:
Calibration
Delays
Training
Linearity
Codes
Phase locked loops
Reinforcement learning
Deep reinforcement learning
circuits calibration
high-dimensional searching
attention scheme
Journal
I
IF:
4.9
Papers:
8.8K
Citations:
2.5W
Organization
Cited Papers
ShareSavePhysico-mechanical, thermal and morphological properties of furfuryl alcohol/2-ethylhexyl methacrylate/halloysite nanoclay wood polymer nanocomposites (WPNCs).png)
Heliyon
OAAI
HeliyonIF0
OAAIShareSaveShareSaveIntraorbital Encephalocele in an Adult Patient Presenting With Pulsatile Exophthalmos -Case Report-OAAI
OAAIShareSaveShareSaveShareSaveMössbauer and positron annihilation studies of structural modifications of hemoglobin in solution
PREAI
ShareSave
View more