Accelerating distributed reinforcement learning with in-switch computing.
Youjie LiIou-Jen LiuYifan YuanDeming ChenAlexander G. SchwingJian HuangPublished in: ISCA (2019)
Keyphrases
- reinforcement learning
- multi agent
- cooperative
- distributed systems
- function approximation
- distributed environment
- mobile agents
- state space
- learning process
- peer to peer
- neural network
- distributed learning
- learning algorithm
- fault tolerant
- robotic control
- optimal policy
- distributed architecture
- temporal difference
- optimal control
- computer networks
- transfer learning
- lightweight
- database systems
- machine learning