RegQ: Convergent Q-Learning with Linear Function Approximation using Regularization

22 Sept 2022, 12:33 (modified: 26 Oct 2022, 14:02)ICLR 2023 Conference Withdrawn SubmissionReaders: Everyone
Keywords: reinforcement learning, Q-learning, reinforcement learning theory
TL;DR: This paper develops convergent Q-learning algorithm when linear function approximation is used.
Abstract: Q-learning is widely used algorithm in reinforcement learning community. Under the lookup table setting, its convergence is well established. However, its behavior is known to be unstable with the linear function approximation case. This paper develops a new Q-learning algorithm, called RegQ, that converges when linear function approximation is used. We prove that simply adding an appropriate regularization term ensures convergence of the algorithm. We prove its stability using a recent analysis tool based on switching system models. Moreover, we experimentally show that RegQ converges in environments where Q-learning with linear function approximation has known to diverge. We also provide an error bound on the solution where the algorithm converges.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)
Supplementary Material: zip
5 Replies