@article{M7EFA7839,
title = "C-COMA: A Continual Reinforcement Learning Model
for Dynamic Multiagent Environments",
journal = "KIPS Transactions on Software and Data Engineering",
year = "2021",
issn = "2287-5905",
doi = "https://doi.org/10.3745/KTSDE.2021.10.4.143",
author = "Kyueyeol Jung/Incheol Kim",
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."
}