Soft Actor-Critic Reinforcement Learning-Based Optimization for Analog Circuit Sizing.
Sejin ParkYoungchang ChoiSeokhyeong KangPublished in: ISOCC (2023)
Keyphrases
- actor critic
- reinforcement learning
- analog circuits
- temporal difference
- approximate dynamic programming
- policy gradient
- optimal control
- function approximation
- reinforcement learning algorithms
- neuro fuzzy
- gradient method
- policy iteration
- dynamic programming
- supervised learning
- fault diagnosis
- neural network
- markov decision processes
- model free
- rl algorithms
- optimization method
- optimization problems
- digital circuits
- average reward
- step size
- state action
- partially observable markov decision processes
- linear program
- dynamical systems
- state space
- expert systems
- machine learning