Abstract
In previous chapters, we review traditional network optimization tools and introduce three learning-based techniques, including the learning-augmented drift method, online learning based algorithms and reinforcement learning. These methods have been receiving an increasing attention, and many new results have been developed based on them. Readers can also see that learning-based models cover a wide range of applications and scenarios in network research.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
P. Auer, N. Cesa-Bianchi, Y. Freund, R.E. Schapire, The nonstochastic multiarmed bandit problem. SIAM J. Comput. 32(1), 48–77 (2002)
H. Gu, X. Guo, X. Wei, R. Xu, Mean-field multi-agent reinforcement learning: a decentralized network approach. arXiv:2018.02731
R. Gummadi, R. Johari, S. Schmit, J. Yu, Mean field analysis of multi-armed bandit games. SSRN (2016)
E. Hazan, Introduction to Online Convex Optimization (MIT Press, 2021)
P. Hu, Y. Chen, L. Huang, Nearly minimax optimal reinforcement learning with linear function approximation, in The Thirty-ninth International Conference on Machine Learning (2022)
P. Hu, L. Pan, Y. Chen, Z. Fang, L. Huang, Effective multi-user delay-constrained scheduling with deep recurrent reinforcement learning, in ACM MobiHoc (2022)
C. Jin, Z. Allen-Zhu, S. Bubeck, M. Jordan, Is Q-learning Provably Efficient? NeurIPS (2018)
Z. Li, X. Wang, L. Pan, L. Zhu, Z. Wang, J. Feng, C. Deng, L. Huang, Network topology optimization via deep reinforcement learning. IEEE Trans. Commun. to appear
J. Li, B. Xia, X. Geng, H. Ming, S. Shakkottai, V. Subramanian, L. Xie, Mean field games in nudge systems for societal networks. ACM Trans. Modeling Perform. Eval. Comput. Syst. (ACM TOMPECS) 3(4), 15 (2018)
Y. Lin, G. Qu, L. Huang, A. Wierman, Multi-agent reinforcement learning in stochastic networked systems. Advances in Neural Information Processing Systems, vol. 34 (2021)
Y. Yang, R. Luo, M. Li, M. Zhou, W. Zhang, J. Wang, Mean field multi-agent reinforcement learning, in Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, PMLR 80 (2018)
D. Zhou, Q. Gu and C. Szepesvári, Nearly minimax optimal reinforcement learning for linear mixture markov decision processes. COLT (2021)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Huang, L. (2023). Summary and Discussions. In: Learning for Decision and Control in Stochastic Networks. Synthesis Lectures on Learning, Networks, and Algorithms. Springer, Cham. https://doi.org/10.1007/978-3-031-31597-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-31597-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-31596-1
Online ISBN: 978-3-031-31597-8
eBook Packages: Synthesis Collection of Technology (R0)eBColl Synthesis Collection 12