GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning.
Hanrui WangKuan WangJiacheng YangLinxiao ShenNan SunHae-Seung LeeSong HanPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- neural network
- high speed
- function approximation
- circuit design
- function approximators
- learning classifier systems
- model free
- reinforcement learning algorithms
- multi agent
- state space
- pattern recognition
- learning capabilities
- power dissipation
- directed graph
- markov decision processes
- temporal difference
- optimal policy
- rl algorithms
- learning agents
- random walk
- learning algorithm
- direct policy search
- low power
- graph structure
- partially observable domains
- integrated circuit
- artificial neural networks
- markov decision process
- machine learning
- learning process
- supervised learning
- reinforcement learning methods
- genetic algorithm
- equivalent circuit
- reinforcement learning problems
- policy search
- multi agent reinforcement learning
- autonomous learning
- policy gradient
- dynamic programming
- action selection
- temporal difference learning
- back propagation
- fault diagnosis
- learning problems
- policy iteration
- radial basis function
- weighted graph