RL-MUL: Multiplier Design Optimization with Deep Reinforcement Learning.
Dongsheng ZuoJiadong ZhuYikang OuyangYuzhe MaPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- function approximation
- model free
- reinforcement learning algorithms
- rl algorithms
- state space
- reinforcement learning methods
- optimal policy
- control problems
- learning algorithm
- temporal difference learning
- floating point
- direct policy search
- machine learning
- temporal difference
- multi agent
- fixed point
- markov decision processes
- hardware implementation
- learning process
- autonomous learning
- optimal control
- markov decision process
- action space
- supervised learning
- partially observable domains
- learning capabilities
- markov decision problems
- approximate dynamic programming
- reinforcement learning agents