Actor-Critic for Multi-agent System with Variable Quantity of Agents.
Gui-hong WangJinglun ShiPublished in: IoTaaS (2018)
Keyphrases
- multi agent systems
- actor critic
- multi agent
- intelligent agents
- single agent
- cooperative
- multiagent systems
- policy gradient
- autonomous agents
- reinforcement learning
- game theory
- function approximation
- gradient method
- multiple agents
- optimal control
- reinforcement learning algorithms
- temporal difference
- trust model
- neuro fuzzy
- policy iteration
- fixed point
- np hard
- approximate dynamic programming
- optimal solution