Keywords: unstable reinforcement learning, LQR, optimization
TL;DR: We propose new methods to effectively improve the convergence of policy gradient method for unstable reinforcement problems.
Abstract: For many of the reinforcement learning applications, the system is assumed to be inherently stable and with bounded reward, state and action space. These are key requirements for the optimization convergence of classical reinforcement learning reward function with discount factors. Unfortunately, these assumptions do not hold true for many real world problems such as an unstable linear–quadratic regulator (LQR). In this work, we propose new methods to stabilize and speed up the convergence of unstable reinforcement learning problems with the policy gradient methods. We provide theoretical insights on the efficiency of our methods. In practice, our method achieve good experimental results over multiple examples where the vanilla methods mostly fail to converge due to system instability.
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.
Supplementary Material: zip
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)