Reinforcement Learning Generalization for Nonlinear Systems Through Dual-Scale Homogeneity Transformations

2023-11-08 · Abdel Gafoor Haddad, Igor Boiko, Yahya Zweiri

Reinforcement learning is an emerging approach to control dynamical systems for which classical approaches are difficult to apply. However, trained agents may not generalize against the variations of system parameters. This paper presents the concept of dual-scale homogeneity, an important property in understating the scaling behavior of nonlinear systems. Furthermore, it also presents an effective yet simple approach to designing a parameter-dependent control law that homogenizes a nonlinear system. The presented approach is applied to two systems, demonstrating its ability to provide a consistent performance irrespective of parameters variations. To demonstrate the practicality of the proposed approach, the control policy is generated by a deep deterministic policy gradient to control the load position of a quadrotor with a slung load. The proposed synergy between the homogeneity transformations and reinforcement learning yields superior performance compared to other recent learning-based control techniques. It achieves a success rate of 96% in bringing the load to its designated target with a 3D RMSE of 0.0253 m. The video that shows the experimental results along with a summary of the paper is available at this link.

📄 PDF Abstract BibTeX arXiv:2311.05013

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning

Sample-efficient diffusion-based control of complex nonlinear systems

2025-02-25 · Hongyi Chen, Jingtao Ding, Jianhai Shu, Xinchun Yu 외

Complex nonlinear system control faces challenges in achieving sample-efficient, reliable performance. While diffusion-based methods have demonstrated advantages over classical and reinforcement learning approaches in lo…

Hybrid Meta-Learning Framework for Anomaly Forecasting in Nonlinear Dynamical Systems via Physics-Inspired Simulation and Deep Ensembles

2025-06-15 · Abdullah Burkan Bereketoglu

We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulato…

Anomaly Detection Anomaly Forecasting Anomaly Localization Meta-Learning+1

Reinforcement Learning State Estimation for High-Dimensional Nonlinear Systems

2021-09-29 · Saviz Mowlavi, Mouhacine Benosman, Saleh Nabi

In high-dimensional nonlinear systems such as fluid flows, the design of state estimators such as Kalman filters relies on a reduced-order model (ROM) of the dynamics. However, ROMs are prone to large errors, which negat…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)State Estimation+1

Structured Control Nets for Deep Reinforcement Learning

2018-02-22 · ICML 2018 7 · Mario Srouji, Jian Zhang, Ruslan Salakhutdinov

In recent years, Deep Reinforcement Learning has made impressive advances in solving several important benchmark problems for sequential decision making. Many control applications use a generic multilayer perceptron (MLP…

Decision Making Deep Reinforcement Learning MuJoCo reinforcement-learning+3

Lyapunov-Based Reinforcement Learning State Estimator

2020-10-26 · Liang Hu, ChengWei Wu, Wei Pan

In this paper, we consider the state estimation problem for nonlinear stochastic discrete-time systems. We combine Lyapunov's method in control theory and deep reinforcement learning to design the state estimator. We the…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1