Abstract
The success story of the DQN agent, which achieved human-level performance in playing Atari games, marked a major breakthrough in the field of artificial intelligence and reinforcement learning. Since then, extensive research and development efforts have been dedicated to building upon the foundations of DQN. Notably, these endeavors have focused on enhancing the network architecture and refining techniques for optimal utilization of experience replay samples.
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
Hado Hasselt. Double q-learning. In J. Lafferty, C. Williams, J. Shawe-Taylor, R. Zemel, and A. Culotta, editors, Advances in Neural Information Processing Systems, volume 23. Curran Associates, Inc., 2010.
Hado van Hasselt, Arthur Guez, and David Silver. Deep reinforcement learning with double q-learning, 2015.
Tom Schaul, John Quan, Ioannis Antonoglou, and David Silver. Prioritized experience replay, 2016.
Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, and Nando de Freitas. Dueling network architectures for deep reinforcement learning, 2016.
Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, and David Silver. Rainbow: Combining improvements in deep reinforcement learning, 2017.
Marc G. Bellemare, Will Dabney, and Rémi Munos. A distributional perspective on reinforcement learning, 2017.
Will Dabney, Georg Ostrovski, David Silver, and Rémi Munos. Implicit quantile networks for distributional reinforcement learning, 2018.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature
About this chapter
Cite this chapter
Hu, M. (2023). Improvements to DQN. In: The Art of Reinforcement Learning. Apress, Berkeley, CA. https://doi.org/10.1007/978-1-4842-9606-6_8
Download citation
DOI: https://doi.org/10.1007/978-1-4842-9606-6_8
Published:
Publisher Name: Apress, Berkeley, CA
Print ISBN: 978-1-4842-9605-9
Online ISBN: 978-1-4842-9606-6
eBook Packages: Professional and Applied ComputingApress Access BooksProfessional and Applied Computing (R0)