paper-with-me

홈 › Papers

Continuous-Time Reinforcement Learning: New Design Algorithms with Theoretical Insights and Performance Guarantees

2023-07-18 · Brent A. Wallace, Jennie Si

Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design method. However, a recent comprehensive analysis of state-of-the-art continuous-time RL (CT-RL) methods, namely, adaptive dynamic programming (ADP)-based CT-RL algorithms, reveals they face significant design challenges due to their complexity, numerical conditioning, and dimensional scaling issues. Despite advanced theoretical results, existing ADP CT-RL synthesis methods are inadequate in solving even small, academic problems. The goal of this work is thus to introduce a suite of new CT-RL algorithms for control of affine nonlinear systems. Our design approach relies on two important factors. First, our methods are applicable to physical systems that can be partitioned into smaller subproblems. This constructive consideration results in reduced dimensionality and greatly improved intuitiveness of design. Second, we introduce a new excitation framework to improve persistence of excitation (PE) and numerical conditioning performance via classical input/output insights. Such a design-centric approach is the first of its kind in the ADP CT-RL community. In this paper, we progressively introduce a suite of (decentralized) excitable integral reinforcement learning (EIRL) algorithms. We provide convergence and closed-loop stability guarantees, and we demonstrate these guarantees on a significant application problem of controlling an unstable, nonminimum phase hypersonic vehicle (HSV).

📄 PDF Abstract BibTeX arXiv:2307.08920

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Reinforcement Learning for Intensity Control: An Application to Choice-Based Network Revenue Management

2024-06-08 · Huiling Meng, Ningyuan Chen, Xuefeng Gao

Intensity control is a type of continuous-time dynamic optimization problems with many important applications in Operations Research including queueing and revenue management. In this study, we adapt the reinforcement le…

Managementreinforcement-learningReinforcement Learning

The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations

2024-01-24 · Matthias Lehmann

In recent years, various powerful policy gradient algorithms have been proposed in deep reinforcement learning. While all these algorithms build on the Policy Gradient Theorem, the specific design choices differ signific…

continuous-controlContinuous ControlDeep Reinforcement LearningLearning Theory

Modulation-Enhanced Excitation for Continuous-Time Reinforcement Learning via Symmetric Kronecker Products

2023-07-31 · Brent A. Wallace, Jennie Si

This work introduces new results in continuous-time reinforcement learning (CT-RL) control of affine nonlinear systems to address a major algorithmic challenge due to a lack of persistence of excitation (PE). This PE des…

reinforcement-learningReinforcement Learning

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL

2021-06-30 · NeurIPS 2021 12 · Jack Parker-Holder, Vu Nguyen, Shaan Desai, Stephen Roberts

Despite a series of recent successes in reinforcement learning (RL), many RL algorithms remain sensitive to hyperparameters. As such, there has recently been interest in the field of AutoRL, which seeks to automate desig…

Data AugmentationHyperparameter OptimizationReinforcement Learning (RL)

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments

2026-06-02 · Saket Tiwari, Tejas Kotwal, George Konidaris arxiv

We present a novel theoretical framework for deep reinforcement learning (RL) in continuous environments by modeling the problem as a continuous-time stochastic process, drawing on insights from stochastic control. Build…

Reinforcement LearningContinuous Control