AutoCkt: Deep Reinforcement Learning of Analog Circuit Designs.
Keertana SettaluriAmeer Haj-AliQijing HuangKourosh HakhamaneshiBorivoje NikolicPublished in: DATE (2020)
Keyphrases
- reinforcement learning
- function approximation
- analog vlsi
- state space
- dynamic programming
- reinforcement learning algorithms
- temporal difference
- optimal control
- markov decision processes
- digital computer
- policy search
- deep learning
- optimal policy
- multi agent
- learning algorithm
- neural network
- high speed
- evolutionary algorithm
- learning capabilities
- learning process
- transition model
- data mining