paper-with-me

홈 › Papers

Koopman-Assisted Reinforcement Learning

2024-03-04 · Preston Rozwood, Edward Mehrez, Ludger Paehler, Wen Sun, Steven L. Brunton

The Bellman equation and its continuous form, the Hamilton-Jacobi-Bellman (HJB) equation, are ubiquitous in reinforcement learning (RL) and control theory. However, these equations quickly become intractable for systems with high-dimensional states and nonlinearity. This paper explores the connection between the data-driven Koopman operator and Markov Decision Processes (MDPs), resulting in the development of two new RL algorithms to address these limitations. We leverage Koopman operator techniques to lift a nonlinear system into new coordinates where the dynamics become approximately linear, and where HJB-based methods are more tractable. In particular, the Koopman operator is able to capture the expectation of the time evolution of the value function of a given system via linear dynamics in the lifted coordinates. By parameterizing the Koopman operator with the control actions, we construct a ``Koopman tensor'' that facilitates the estimation of the optimal value function. Then, a transformation of Bellman's framework in terms of the Koopman tensor enables us to reformulate two max-entropy RL algorithms: soft value iteration and soft actor-critic (SAC). This highly flexible framework can be used for deterministic or stochastic systems as well as for discrete or continuous-time dynamics. Finally, we show that these Koopman Assisted Reinforcement Learning (KARL) algorithms attain state-of-the-art (SOTA) performance with respect to traditional neural network-based SAC and linear quadratic regulator (LQR) baselines on four controlled dynamical systems: a linear state-space system, the Lorenz system, fluid flow past a cylinder, and a double-well potential with non-isotropic stochastic forcing.

📄 PDF Abstract BibTeX arXiv:2403.02290

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Dilated Convolution 설명 없음
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
SAC 설명 없음

Similar Papers 제목 키워드 기반

Koopman-Based Generalization of Deep Reinforcement Learning With Application to Wireless Communications

2025-03-04 · Atefeh Termehchi, Ekram Hossain, Isaac Woungang

Deep Reinforcement Learning (DRL) is a key machine learning technology driving progress across various scientific and engineering fields, including wireless communication. However, its limited interpretability and genera…

Deep Reinforcement Learning

Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces

2022-08-16 · Tomoharu Iwata, Yoshinobu Kawahara

We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning

2026-07-13 · Evelyn D'Elia, Weishu Zhan, Giulio Turrisi, Giulio Romualdi 외 arxiv

Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency. In robotics, a recent line of work has emerged addressing this problem by encoding physics priors in the learning process. However, m…

Reinforcement Learning

Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performance

2025-05-12 · Md Nur-A-Adam Dony

This study presents an innovative approach to Model Predictive Control (MPC) by leveraging the powerful combination of Koopman theory and Deep Reinforcement Learning (DRL). By transforming nonlinear dynamical systems int…

Deep Reinforcement LearningModel Predictive Control

Task-Oriented Koopman-Based Control with Contrastive Encoder

2023-09-28 · Xubo Lyu, Hanyang Hu, Seth Siriya, Ye Pu 외

We present task-oriented Koopman-based control that utilizes end-to-end reinforcement learning and contrastive encoder to simultaneously learn the Koopman latent embedding, operator, and associated linear controller with…

reinforcement-learning