Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach.
Bin ZhangHangyu MaoJingqing RuanYing WenYang LiShao ZhangZhiwei XuDapeng LiZiyue LiRui ZhaoLijuan LiGuoliang FanPublished in: CoRR (2023)
Keyphrases
- decision making
- actor critic
- action selection
- reinforcement learning
- multi agent systems
- temporal difference
- multi agent
- decision makers
- policy gradient
- fuzzy logic
- single agent
- model free
- function approximation
- multiple agents
- optimal control
- data mining
- neuro fuzzy
- dynamic environments
- incomplete information
- supply chain
- policy iteration
- cooperative
- neural network