Download pdf
Adaptive Multi-layer Attention Double Dueling Deep Q-Network for Muti-agent Reinforcement Learning
- 1 School of AI and Advanced Computing, XJTLU College, SuZhou, China
* Author to whom correspondence should be addressed.
Abstract
In multi-agent fields, traditional muti-agent DQN methods often suffer from overestimation bias and overestimation of unimportant actions, especially when state-action Q-value differences are slight. To deal with such issue, we present an adaptive Multi-layer Attention Double Dueling Deep Q-Network (MAD-D3QN) model, aiming to improve decision-making accuracy in complex multi-agent environments. The proposed model utilizes two attention layers that dynamically calculate state value and action advantage weights, facilitating more precise Q-value estimation and reducing the common overestimation bias. Related experiments carried out in StarWar II scenarios show that the MAD-D3QN model obviously outperforms traditional methods (IQL,DQN), achieving higher decision efficiency and robustness. Our findings demonstrates that the MAD-D3QN framework not only promotes the state-of-the-art in multi-agent reinforcement learning but also provides potential applications in real-world cooperative tasks. Future research will delve into the integration of advanced multi-agent communication structures to further enhance model adaptability.
Keywords
Multi-Agent Systems, Double DQN, Dueling DQN, D3QN, Attention Mechanisms.
[1]. Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., & Hassabis, D. (2015). Human-level control through deep reinforcement learning. Nature, 518(7540), 529-533.
[2]. Hafiz, A. M., & Bhat, G. M. (2020). Deep Q-Network based multi-agent reinforcement learning withbinary action agents. arXiv preprint arXiv:2008.04109.
[3]. Rashid, T., Samvelyan, M., de Witt, C. S., Farquhar, G., Foerster, J., & Whiteson, S. (2018). QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning. Proceedings of the 35th International Conference on Machine Learning, PMLR, 80, 4292-4301.
[4]. Sunehag, P., Lever, G., Gruslys, A., Czarnecki, W. M., Zambaldi, V., Jaderberg, M., ... & Blundell, C. (2018). Value-decomposition networks for cooperative multi-agent learning. arXiv preprint arXiv:1706.05296.
[5]. He, Y., Mu, C., & Sun, Y. (2023). Enhancing Intersection Signal Control: Distributional Double Dueling Deep Q-learning Network with Priority Experience Replay and NoisyNet Approach. 2023 19th International Conference on Mobility, Sensing and Networking (MSN), Mobility, Sensing and Networking (MSN), 2023 19th International Conference on, MSN, 794–799. https://doi-org.ez.xjtlu.edu.cn/10.1109/MSN60784.2023.00116
[6]. Zhang, K., Yang, Z., & Başar, T. (2019). Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms.
[7]. Lou, Z., Wang, Y., Shan, S., Zhang, K., & Wei, H. (2024). Balanced prioritized experience replay in off-policy reinforcement learning. Neural Computing and Applications, 36(25), 15721–15737. https://doi-org.ez.xjtlu.edu.cn/10.1007/s00521-024-09913-6
[8]. Rashid, T., Samvelyan, M., de Witt, C. S., Farquhar, G., Foerster, J., & Whiteson, S. (2020). Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning.
[9]. Kallinteris, A., Orfanoudakis, S., & Chalkiadakis, G. (2024). A comprehensive analysis of agent factorization and learning algorithms in multiagent systems. Autonomous Agents & Multi-Agent Systems, 38(2), 1-48.
[10]. Foerster, J., Farquhar, G., Afouras, T., Nardelli, N., & Whiteson, S. (2018). Counterfactual multi-agent policy gradients. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).
[11]. Yu, W., Wang, R., & Hu, X. (2023). Learning Attentional Communication with a Common Network for Multiagent Reinforcement Learning. Computational Intelligence & Neuroscience, 1–12. https://doi-org.ez.xjtlu.edu.cn/10.1155/2023/5814420
Cite this article
Jiang,J. (2024). Adaptive Multi-layer Attention Double Dueling Deep Q-Network for Muti-agent Reinforcement Learning. Applied and Computational Engineering,103,211-219.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 2nd International Conference on Machine Learning and Automation
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).