Bi-Level Actor-Critic for Multi-Agent Coordination.
Haifeng ZhangWeizhe ChenZeren HuangMinne LiYaodong YangWeinan ZhangJun WangPublished in: AAAI (2020)
Keyphrases
- bi level
- multi agent coordination
- actor critic
- reinforcement learning
- single agent
- policy gradient
- multi agent
- optimal control
- temporal difference
- approximate dynamic programming
- neuro fuzzy
- multiple agents
- gray scale
- gradient method
- reinforcement learning algorithms
- policy iteration
- function approximation
- multi agent systems
- average reward
- linear program
- evaluation function
- state space
- dynamic environments
- markov decision processes
- machine learning
- path finding
- fuzzy rules
- image compression