Cooperative Multi-Agent Deep Reinforcement Learning with Counterfactual Reward

In partially observable fully cooperative games, agents generally tend to maximize global rewards with joint actions, so it is difficult for each agent to deduce their own contribution. To address this credit assignment problem, we propose a multi-agent reinforcement learning algorithm with counterf...

Full description

Bibliographic Details

Published in:	Proceedings of ... International Joint Conference on Neural Networks pp. 1 - 8
Main Authors:	Shao, Kun, Zhu, Yuanheng, Tang, Zhentao, Zhao, Dongbin
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.07.2020
Subjects:	Collaboration cooperative games counterfactual reward deep reinforcement learning Games Learning (artificial intelligence) Machine learning Multi-agent systems reinforcement learning Task analysis Training
ISSN:	2161-4407
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!