Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning.
Xiangyu KongBo XinFangchen LiuYizhou WangPublished in: CoRR (2017)
Keyphrases
- master slave
- reinforcement learning
- multi agent
- state space
- robotic arm
- laparoscopic surgery
- learning algorithm
- cooperative
- function approximation
- agent oriented
- markov decision processes
- single agent
- multi agent environments
- dynamic programming
- reinforcement learning algorithms
- machine learning
- intelligent agents
- multi agent systems
- optimal control
- autonomous agents
- markov decision process
- management system
- multi agent architecture
- policy search
- neural network
- multi agent platform