Researches advanced in multi-agent credit assignment in reinforcement learning

Yuzheng Wu

doi:10.1117/12.2641860

10 November 2022 Researches advanced in multi-agent credit assignment in reinforcement learning

Yuzheng Wu

Proceedings Volume 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022); 123482U (2022) https://doi.org/10.1117/12.2641860
Event: 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 2022, Zhuhai, China

Abstract

The multi-agent system (MAS) has always been one of the hot tasks in the distributed computing community. While with the development of reinforcement learning, the novel Multi-agent Reinforcement Learning (MARL) has gradually attracted more researchers’ attention, which aims to solve complex real-time tasks in dynamic multi-agent environment by their interaction and has been widely used in robotics, human-computer match, automatic driving and so on. Different from simple single-agent reinforcement learning, MARL faces some challenges due to the complex relationships among agents and the most influential one is the issue of credit assignment. The credit assignment often causes a substantial impediment to reward distribution, which is because the model only generates the global rewards while the own credit of each individual agent is needed during the model training phase. How to estimate and deduce the reward for each agent becomes a key issue in MARL. According to the difference of strategies, in this paper, we present an overview of the main approaches for credit assignment in MARL from three aspects, including the value-based algorithm, policy-based algorithm and mixing network-based algorithm. Also, this paper makes performance comparisons among these algorithms in different multi-agent experimental environments and finishes basic evaluation of approaches by analyzing the results of experiments. Finally, this paper summarizes the main challenges in multi-agent credit assignment (MACA) with their related solutions, current defects of algorithms about these challenges, and prospects the possible future development direction of the MACA.

Citation Download Citation

Yuzheng Wu "Researches advanced in multi-agent credit assignment in reinforcement learning", Proc. SPIE 12348, 2nd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2022), 123482U (10 November 2022); https://doi.org/10.1117/12.2641860

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Monochromatic aberrations

Algorithm development

Stochastic processes

Performance modeling

Systems modeling

Analytical research

Control systems

Show All Keywords

Keywords/Phrases

Search In:

Publication Years