Expert System-Based Multiagent Deep Deterministic Policy Gradient for Swarm Robot Decision Making.
Zhen WangXiaoyue JinTao ZhangJiahao LiDengxiu YuKang Hao CheongC. L. Philip ChenPublished in: IEEE Trans. Cybern. (2024)
Keyphrases
- policy gradient
- expert systems
- decision making
- multi agent
- single agent
- mobile robot
- reinforcement learning
- fuzzy logic
- cooperative
- actor critic
- decision makers
- multiagent systems
- function approximation
- optimal control
- particle swarm optimization
- real robot
- multiple agents
- stochastic games
- model free reinforcement learning
- dynamic environments
- knowledge base
- average reward
- multi agent systems
- reinforcement learning algorithms
- path planning
- gradient method
- state action
- neural network
- markov decision processes
- action selection
- variance reduction
- learning algorithm
- temporal difference
- robot arm