mlsanityData to 14 Oct 2026

A modular framework for stabilizing deep reinforcement learning control

arXiv 2304.03422 ↗First posted 7 Apr 2023eess.SY cs.LG cs.SYcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a framework for the design of feedback controllers that combines the optimization-driven and model-free advantages of deep reinforcement learning with the stability guarantees provided by using the Youla-Kucera parameterization to define the search domain. Recent advances in behavioral systems allow us to construct a data-driven internal model; this enables an alternative realization of the Youla-Kucera parameterization based entirely on input-output exploration data. Using a neural network to express a parameterized set of nonlinear stable operators enables seamless integration with standard deep learning libraries. We demonstrate the approach on a realistic simulation of a two-tank system.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 12 of its 24 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

12 of 24 references.

References · 12

  1. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  2. 2016Input Convex Neural Networkscited by 414
  3. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  4. 2019Safe Reinforcement Learning Using Robust MPCcited by 85
  5. 2020Actor-Critic Reinforcement Learning for Control with Stability Guaranteecited by 45
  6. 2021Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustnesscited by 45
  7. 2018Stability-certified reinforcement learning: A control-theoretic perspectivecited by 31
  8. 2021Deep Reinforcement Learning with Shallow Controllers: An Experimental Application to PID Tuningcited by 24
  9. 2021Almost Surely Stable Deep Dynamicscited by 16
  10. 2021Learning over All Stabilizing Nonlinear Controllers for a Partially-Observed Linear Systemcited by 14
  11. 2019A trajectory-based framework for data-driven system analysis and controlcited by 11
  12. 2020Willems' Fundamental Lemma for State-space Systems and its Extension to Multiple Datasetscited by 8

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behaviorcited by 3