A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents

A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents

Multi-agent reinforcement learning (MARL) can be used to design intelligent agents for solving cooperative tasks. Within the MARL category, this paper proposes the probability of maximal reward based on the infinitesimal gradient ascent (PMR-IGA) algorithm to reach the maximal total reward in repeat...

Full description

Bibliographic Details
Main Authors: Zhen Zhang, Dongqing Wang, Dongbin Zhao, Qiaoni Han, Tingting Song
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Multi-agent reinforcement learning
gradient ascent
Q-learning
cooperative tasks
Online Access:https://ieeexplore.ieee.org/document/8517104/

Internet

https://ieeexplore.ieee.org/document/8517104/

Similar Items