Device-system Co-design of Photonic Neuromorphic Processor using Reinforcement Learning.
Yingheng TangPrincess Tara ZamaniRuiyang ChenJianzhu MaMinghao QiCunxi YuWeilu GaoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- physical characteristics
- high speed
- function approximation
- learning algorithm
- model free
- robotic control
- reinforcement learning algorithms
- parallel processing
- state space
- reinforcement learning methods
- action selection
- optimal control
- real time
- learning problems
- temporal difference learning
- markov decision processes
- read write
- multi agent reinforcement learning
- multi agent
- multiprocessor systems
- machine learning