C-COMA: A Continual Reinforcement Learning Model for Dynamic Multiagent Environments


KIPS Transactions on Software and Data Engineering, Vol. 10, No. 4, pp. 143-152, Apr. 2021
https://doi.org/10.3745/KTSDE.2021.10.4.143,   PDF Download:  
Keywords: Multiagent Reinforcement Learning, Dynamic Environment, Continual Learning, Starcraft II
Abstract

It is very important to learn behavioral policies that allow multiple agents to work together organically for common goals in various real-world applications. In this multi-agent reinforcement learning (MARL) environment, most existing studies have adopted centralized training with decentralized execution (CTDE) methods as in effect standard frameworks. However, this multi-agent reinforcement learning method is difficult to effectively cope with in a dynamic environment in which new environmental changes that are not experienced during training time may constantly occur in real life situations. In order to effectively cope with this dynamic environment, this paper proposes a novel multi-agent reinforcement learning system, C-COMA. C-COMA is a continual learning model that assumes actual situations from the beginning and continuously learns the cooperative behavior policies of agents without dividing the training time and execution time of the agents separately. In this paper, we demonstrate the effectiveness and excellence of the proposed model C-COMA by implementing a dynamic mini-game based on Starcraft II, a representative real-time strategy game, and conducting various experiments using this environment.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
K. Jung and I. Kim, "C-COMA: A Continual Reinforcement Learning Model for Dynamic Multiagent Environments," KIPS Transactions on Software and Data Engineering, vol. 10, no. 4, pp. 143-152, 2021. DOI: https://doi.org/10.3745/KTSDE.2021.10.4.143.

[ACM Style]
Kyueyeol Jung and Incheol Kim. 2021. C-COMA: A Continual Reinforcement Learning Model for Dynamic Multiagent Environments. KIPS Transactions on Software and Data Engineering, 10, 4, (2021), 143-152. DOI: https://doi.org/10.3745/KTSDE.2021.10.4.143.