Noise-Regularized Advantage Value for Multi-Agent Reinforcement Learning

Noise-Regularized Advantage Value for Multi-Agent Reinforcement Learning

Leveraging global state information to enhance policy optimization is a common approach in multi-agent reinforcement learning (MARL). Even with the supplement of state information, the agents still suffer from insufficient exploration in the training stage. Moreover, training with batch-sampled exam...

Full description

Bibliographic Details
Main Authors: Siying Wang, Wenyu Chen, Jian Hu, Siyue Hu, Liwei Huang
Format: Article
Language:English
Published: MDPI AG 2022-08-01
Series:Mathematics
Subjects:
multi-agent reinforcement learning
proximal policy optimization
exploration
noise injection
advantage function
Online Access:https://www.mdpi.com/2227-7390/10/15/2728

Internet

https://www.mdpi.com/2227-7390/10/15/2728

Similar Items