Bi-level Actor-Critic for Multi-agent Coordination.
Haifeng ZhangWeizhe ChenZeren HuangMinne LiYaodong YangWeinan ZhangJun WangPublished in: CoRR (2019)
Keyphrases
- bi level
- multi agent coordination
- actor critic
- reinforcement learning
- policy gradient
- single agent
- multi agent
- optimal control
- temporal difference
- approximate dynamic programming
- neuro fuzzy
- gradient method
- multiple agents
- gray scale
- reinforcement learning algorithms
- policy iteration
- function approximation
- average reward
- cooperative
- multi agent systems
- decision problems
- dynamic programming
- model free
- markov decision processes
- action selection
- evaluation function
- linear program
- least squares
- multiscale