Translator Disclaimer
Poster + Presentation + Paper
12 April 2021 Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training
Piyush K. Sharma, Rolando Fernandez, Erin Zaroukian, Michael Dorothy, Anjon Basak, Derrik E. Asher
Author Affiliations +
Conference Poster
Abstract
Much work has been dedicated to the exploration of Multi-Agent Reinforcement Learning (MARL) paradigms implementing a centralized learning with decentralized execution approach to improve human-like collaboration in cooperative tasks. Here, we introduce variations of centralized training to describe cases where shared/independent reward structure is utilized to improve learning by training agents in an intelligent way, and to analyze cooperative behavior in multi-agent systems. This work discusses implications for providing a classification of the recent MARL algorithmic approaches on the basis of their information sharing mechanism (e.g., reward, gradient, action, parameter, observation/state space sharing) on cooperative behavior in multi-agent systems.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Piyush K. Sharma, Rolando Fernandez, Erin Zaroukian, Michael Dorothy, Anjon Basak, and Derrik E. Asher "Survey of recent multi-agent reinforcement learning algorithms utilizing centralized training", Proc. SPIE 11746, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications III, 117462K (12 April 2021); https://doi.org/10.1117/12.2585808
PROCEEDINGS
12 PAGES + POSTER + PRESENTATION

SHARE
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
KEYWORDS
Artificial intelligence

Classification systems

Intelligence systems

RELATED CONTENT

Knomes: Knowledge Monitoring Expert System
Proceedings of SPIE (October 31 1987)
Fuzzy concept formation
Proceedings of SPIE (March 01 1992)
ANN-TREE: a hybrid method for pattern recognition
Proceedings of SPIE (September 02 1993)

Back to Top