Stable Modular Control via Contraction Theory for Reinforcement Learning

• URL: http://arxiv.org/abs/2311.03669v1
• Date: Tue, 7 Nov 2023 02:41:02 GMT
• Title: Stable Modular Control via Contraction Theory for Reinforcement Learning
• Authors: Bing Song, Jean-Jacques Slotine, Quang-Cuong Pham
• Abstract summary: We propose a novel way to integrate control techniques with reinforcement learning (RL) for stability, robustness, and generalization. We realize such modularity via signal composition and dynamic decomposition.
• Score: 8.742125999252366
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel way to integrate control techniques with reinforcement learning (RL) for stability, robustness, and generalization: leveraging contraction theory to realize modularity in neural control, which ensures that combining stable subsystems can automatically preserve the stability. We realize such modularity via signal composition and dynamic decomposition. Signal composition creates the latent space, within which RL applies to maximizing rewards. Dynamic decomposition is realized by coordinate transformation that creates an auxiliary space, within which the latent signals are coupled in the way that their combination can preserve stability provided each signal, that is, each subsystem, has stable self-feedbacks. Leveraging modularity, the nonlinear stability problem is deconstructed into algebraically solvable ones, the stability of the subsystems in the auxiliary space, yielding linear constraints on the input gradients of control networks that can be as simple as switching the signs of network weights. This minimally invasive method for stability allows arguably easy integration into the modular neural architectures in machine learning, like hierarchical RL, and improves their performance. We demonstrate in simulation the necessity and the effectiveness of our method: the necessity for robustness and generalization, and the effectiveness in improving hierarchical RL for manipulation learning.

Related papers

• Learning to Boost the Performance of Stable Nonlinear Systems [0.0]
  We tackle the performance-boosting problem with closed-loop stability guarantees. Our methods enable learning over arbitrarily deep neural network classes of performance-boosting controllers for stable nonlinear systems.
  arXiv  Detail & Related papers  (2024-05-01T21:11:29Z)
• Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation [67.63756749551924]
  Learning-based neural network (NN) control policies have shown impressive empirical performance in a wide range of tasks in robotics and control. Lyapunov stability guarantees over the region-of-attraction (ROA) for NN controllers with nonlinear dynamical systems are challenging to obtain. We demonstrate a new framework for learning NN controllers together with Lyapunov certificates using fast empirical falsification and strategic regularizations.
  arXiv  Detail & Related papers  (2024-04-11T17:49:15Z)
• Distributionally Robust Model-based Reinforcement Learning with Large State Spaces [55.14361269378122]
  Three major challenges in reinforcement learning are the complex dynamical systems with large state spaces, the costly data acquisition processes, and the deviation of real-world dynamics from the training environment deployment. We study distributionally robust Markov decision processes with continuous state spaces under the widely used Kullback-Leibler, chi-square, and total variation uncertainty sets. We propose a model-based approach that utilizes Gaussian Processes and the maximum variance reduction algorithm to efficiently learn multi-output nominal transition dynamics.
  arXiv  Detail & Related papers  (2023-09-05T13:42:11Z)
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence [59.11038175596807]
  Continual learning aims to empower artificial intelligence with strong adaptability to the real world. Existing advances mainly focus on preserving memory stability to overcome catastrophic forgetting. We propose a generic approach that appropriately attenuates old memories in parameter distributions to improve learning plasticity.
  arXiv  Detail & Related papers  (2023-08-29T02:43:58Z)
• Data-Driven Control with Inherent Lyapunov Stability [3.695480271934742]
  We propose Control with Inherent Lyapunov Stability (CoILS) as a method for jointly learning parametric representations of a nonlinear dynamics model and a stabilizing controller from data. In addition to the stabilizability of the learned dynamics guaranteed by our novel construction, we show that the learned controller stabilizes the true dynamics under certain assumptions on the fidelity of the learned dynamics.
  arXiv  Detail & Related papers  (2023-03-06T14:21:42Z)
• Formal Controller Synthesis for Markov Jump Linear Systems with Uncertain Dynamics [64.72260320446158]
  We propose a method for synthesising controllers for Markov jump linear systems. Our method is based on a finite-state abstraction that captures both the discrete (mode-jumping) and continuous (stochastic linear) behaviour of the MJLS. We apply our method to multiple realistic benchmark problems, in particular, a temperature control and an aerial vehicle delivery problem.
  arXiv  Detail & Related papers  (2022-12-01T17:36:30Z)
• KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems [66.9461097311667]
  We propose a model-based reinforcement learning framework with formal stability guarantees. The proposed method learns the system dynamics up to a confidence interval using feature representation. We show that KCRL is guaranteed to learn a stabilizing policy in a finite number of interactions with the underlying unknown system.
  arXiv  Detail & Related papers  (2022-06-03T17:27:04Z)
• Total Energy Shaping with Neural Interconnection and Damping Assignment -- Passivity Based Control [2.1485350418225244]
  We exploit the universal approximation property of Neural Networks (NNs) to design passivity-based control schemes. The proposed control design methodology is validated for mechanical systems of one and two degrees-of-freedom.
  arXiv  Detail & Related papers  (2021-12-24T08:41:17Z)
• Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics [90.81186513537777]
  We propose a novel compound kernel that captures the control-affine nature of the problem. We show that this resulting optimization problem is convex, and we call it Gaussian Process-based Control Lyapunov Function Second-Order Cone Program (GP-CLF-SOCP)
  arXiv  Detail & Related papers  (2020-11-14T01:27:32Z)
• Imposing Robust Structured Control Constraint on Reinforcement Learning of Linear Quadratic Regulator [0.0]
  This paper presents a design for any generic structure, paving the way for distributed learning control. The ideas from reinforcement learning (RL) in conjunction with control-theoretic sufficient stability and performance guarantees are used to develop the methodology. We validate our theoretical results with a simulation on a multi-agent network with 6 agents.
  arXiv  Detail & Related papers  (2020-11-12T00:31:39Z)
• Reinforcement Learning of Structured Control for Linear Systems with Unknown State Matrix [0.0]
  We bring forth the ideas from reinforcement learning (RL) in conjunction with sufficient stability and performance guarantees. A special control structure enabled by this RL framework is distributed learning control which is necessary for many large-scale cyber-physical systems.
  arXiv  Detail & Related papers  (2020-11-02T17:04:34Z)

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.