A stabilizing reinforcement learning approach for sampled systems with partially unknown models

• URL: http://arxiv.org/abs/2208.14714v1
• Date: Wed, 31 Aug 2022 09:20:14 GMT
• Title: A stabilizing reinforcement learning approach for sampled systems with partially unknown models
• Authors: Lukas Beckenbach, Pavel Osinenko, Stefan Streif
• Abstract summary: We suggest a method to guarantee practical stability of the system-controller closed loop in a purely online learning setting. To achieve the claimed results, we employ techniques of classical adaptive control. The method is tested in adaptive traction control and cruise control where it proved to significantly reduce the cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reinforcement learning is commonly associated with training of reward-maximizing (or cost-minimizing) agents, in other words, controllers. It can be applied in model-free or model-based fashion, using a priori or online collected system data to train involved parametric architectures. In general, online reinforcement learning does not guarantee closed loop stability unless special measures are taken, for instance, through learning constraints or tailored training rules. Particularly promising are hybrids of reinforcement learning with "classical" control approaches. In this work, we suggest a method to guarantee practical stability of the system-controller closed loop in a purely online learning setting, i.e., without offline training. Moreover, we assume only partial knowledge of the system model. To achieve the claimed results, we employ techniques of classical adaptive control. The implementation of the overall control scheme is provided explicitly in a digital, sampled setting. That is, the controller receives the state of the system and computes the control action at discrete, specifically, equidistant moments in time. The method is tested in adaptive traction control and cruise control where it proved to significantly reduce the cost.

Related papers

• Improving the Performance of Robust Control through Event-Triggered Learning [74.57758188038375]
  We propose an event-triggered learning algorithm that decides when to learn in the face of uncertainty in the LQR problem. We demonstrate improved performance over a robust controller baseline in a numerical example.
  arXiv  Detail & Related papers  (2022-07-28T17:36:37Z)
• Sparsity in Partially Controllable Linear Systems [56.142264865866636]
  We study partially controllable linear dynamical systems specified by an underlying sparsity pattern. Our results characterize those state variables which are irrelevant for optimal control.
  arXiv  Detail & Related papers  (2021-10-12T16:41:47Z)
• Stable Online Control of Linear Time-Varying Systems [49.41696101740271]
  COCO-LQ is an efficient online control algorithm that guarantees input-to-state stability for a large class of LTV systems. We empirically demonstrate the performance of COCO-LQ in both synthetic experiments and a power system frequency control example.
  arXiv  Detail & Related papers  (2021-04-29T06:18:49Z)
• Closing the Closed-Loop Distribution Shift in Safe Imitation Learning [80.05727171757454]
  We treat safe optimization-based control strategies as experts in an imitation learning problem. We train a learned policy that can be cheaply evaluated at run-time and that provably satisfies the same safety guarantees as the expert.
  arXiv  Detail & Related papers  (2021-02-18T05:11:41Z)
• Learning-based vs Model-free Adaptive Control of a MAV under Wind Gust [0.2770822269241973]
  Navigation problems under unknown varying conditions are among the most important and well-studied problems in the control field. Recent model-free adaptive control methods aim at removing this dependency by learning the physical characteristics of the plant directly from sensor feedback. We propose a conceptually simple learning-based approach composed of a full state feedback controller, tuned robustly by a deep reinforcement learning framework.
  arXiv  Detail & Related papers  (2021-01-29T10:13:56Z)
• Extended Radial Basis Function Controller for Reinforcement Learning [3.42658286826597]
  This paper proposes a hybrid reinforcement learning controller which dynamically interpolates a model-based linear controller and an arbitrary differentiable policy. The linear controller is designed based on local linearised model knowledge, and stabilises the system in a neighbourhood about an operating point. Learning has been done on both model-based (PILCO) and model-free (DDPG) frameworks.
  arXiv  Detail & Related papers  (2020-09-12T20:56:48Z)
• Fault-Tolerant Control of Degrading Systems with On-Policy Reinforcement Learning [1.8799681615947088]
  We propose a novel adaptive reinforcement learning control approach for fault tolerant systems. Online and offline learning are combined to improve exploration and sample efficiency. We conduct experiments on an aircraft fuel transfer system to demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-08-10T20:42:59Z)
• Anticipating the Long-Term Effect of Online Learning in Control [75.6527644813815]
  AntLer is a design algorithm for learning-based control laws that anticipates learning. We show that AntLer approximates an optimal solution arbitrarily accurately with probability one.
  arXiv  Detail & Related papers  (2020-07-24T07:00:14Z)
• Learning Constrained Adaptive Differentiable Predictive Control Policies With Guarantees [1.1086440815804224]
  We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems. We employ automatic differentiation to obtain direct policy gradients by backpropagating the model predictive control (MPC) loss function and constraints penalties through a differentiable closed-loop system dynamics model.
  arXiv  Detail & Related papers  (2020-04-23T14:24:44Z)
• Model-Reference Reinforcement Learning Control of Autonomous Surface Vehicles with Uncertainties [1.7033108359337459]
  The proposed control combines a conventional control method with deep reinforcement learning. With the reinforcement learning, we can directly learn a control law to compensate for modeling uncertainties. In comparison with traditional deep reinforcement learning methods, our proposed learning-based control can provide stability guarantees and better sample efficiency.
  arXiv  Detail & Related papers  (2020-03-30T22:02:13Z)
• Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems [91.43582419264763]
  We study the problem of system identification and adaptive control in partially observable linear dynamical systems. We present the first model estimation method with finite-time guarantees in both open and closed-loop system identification. We show that AdaptOn is the first algorithm that achieves $textpolylogleft(Tright)$ regret in adaptive control of unknown partially observable linear dynamical systems.
  arXiv  Detail & Related papers  (2020-03-25T06:00:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.