RL-MUL: Multiplier Design Optimization with Deep Reinforcement Learning.
Dongsheng ZuoYikang OuyangYuzhe MaPublished in: DAC (2023)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- state space
- learning algorithm
- learning problems
- rl algorithms
- markov decision processes
- floating point
- temporal difference
- reinforcement learning methods
- control problems
- optimal policy
- multi agent
- dynamic programming
- type ii
- optimal control
- supervised learning
- learning agents
- learning process
- exploration exploitation
- continuous state and action spaces
- complex domains
- policy iteration
- action space
- temporal difference learning
- reinforcement learning problems
- partially observable domains