Towards Provable Control for Unknown Linear Dynamical Systems
We study the control of symmetric linear dynamical systems with unknown dynamics and a hidden state. Using a recent spectral filtering technique for concisely representing such systems in a linear basis, we formulate optimal control in this setting as a convex program. This approach eliminates the need to solve the non-convex problem of explicit identification of the system and its latent state, and allows for provable optimality guarantees for the control signal. We give the first efficient algorithm for finding the optimal control signal with an arbitrary time horizon T, with sample complexity (number of training rollouts) polynomial only in log(T) and other relevant parameters.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Safe Reinforcement Learning via Recovery-based Shielding with Gaussian Process Dynamics Models
Reinforcement learning (RL) is a powerful framework for optimal decision-making and control but often lacks provable guarantees for safety-critical applications. In this paper, we introduce a novel recovery-based shieldi…
Reinforcement LearningContinuous ControlNeural Koopman Lyapunov Control
Learning and synthesizing stabilizing controllers for unknown nonlinear control systems is a challenging problem for real-world and industrial applications. Koopman operator theory allows one to analyze nonlinear systems…
Neural Incremental Input-to-State Stable Control Lyapunov Functions for Unknown Continuous-time Systems
This work primarily focuses on synthesizing a controller that guarantees an unknown continuous-time system to be incrementally input-to-state stable ($\delta$-ISS). In this context, the notion of $\delta$-ISS control Lya…
Conformal Reachability for Safe Control in Unknown Environments
Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space ar…
Change Point Detection Approach for Online Control of Unknown Time Varying Dynamical Systems
We propose a novel change point detection approach for online learning control with full information feedback (state, disturbance, and cost feedback) for unknown time-varying dynamical systems. We show that our algorithm…
Change Point Detection