MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning
Abstract
Distributed decision-making in multi-agent systems presents difficult challenges for interactive behavior learning in both cooperative and competitive systems. To mitigate this complexity, MAIDRL presents a semi-centralized Dense Reinforcement Learning algorithm enhanced by agent influence maps (AIMs), for learning effective multi-agent control on StarCraft Multi-Agent Challenge (SMAC) scenarios. In this paper, we extend the DenseNet in MAIDRL and introduce semi-centralized Multi-Agent Dense-CNN Reinforcement Learning, MAIDCRL, by incorporating convolutional layers into the deep model architecture, and evaluate the performance on both homogeneous and heterogeneous scenarios. The results show that the CNN-enabled MAIDCRL significantly improved the learning performance and achieved a faster learning rate compared to the existing MAIDRL, especially on more complicated heterogeneous SMAC scenarios. We further investigate the stability and robustness of our model. The statistics reflect that our model not only achieves higher winning rate in all the given scenarios but also boosts the agent's learning process in fine-grained decision-making.
Department(s)
Computer Science
Document Type
Conference Proceeding
DOI
10.1109/CoG51982.2022.9893711
Keywords
convolutional neural network, Deep reinforcement learning, MAIDRL, multi-agent system, StarCraft II
Publication Date
1-1-2022
Recommended Citation
Nipu, Ayesha Siddika; Liu, Siming; and Harris, Anthony, "MAIDCRL: Semi-centralized Multi-Agent Influence Dense-CNN Reinforcement Learning" (2022). Faculty Scholarship. 810.
https://bearworks.missouristate.edu/articles00/810
Journal Title
IEEE Conference on Computatonal Intelligence and Games Cig
