A Framework for Adaptive Stabilisation of Nonlinear Stochastic Systems
We consider the adaptive control problem for discrete-time, nonlinear stochastic systems with linearly parameterised uncertainty. Assuming access to a parameterised family of controllers that can stabilise the system in a bounded set within an informative region of the state space when the parameter is well-chosen, we propose a certainty equivalence learning-based adaptive control strategy, and subsequently derive stability bounds on the closed-loop system that hold for some probabilities. We then show that if the entire state space is informative, and the family of controllers is globally stabilising with appropriately chosen parameters, high probability stability guarantees can be derived.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Nonlinear feedback stabilisation and stochastic disturbance suppression of actively Q-switched lasers
Actively Q-switched lasers are widely used tools which are required to produce stable output pulse energies for many applications. In this paper, a model-based control concept for actively Q-switched lasers is presented …
GIFT: Global stabilisation via Intrinsic Fine Tuning
Deep reinforcement learning policies achieve strong performance in complex continuous control environments with nonlinear contact forces. However, these policies often produce chaotic state dynamics, with trivially small…
Reinforcement LearningContinuous ControlLyapunov-Based Deep Neural Networks for Adaptive Control of Stochastic Nonlinear Systems
Controlling nonlinear stochastic dynamical systems involves substantial challenges when the dynamics contain unknown and unstructured nonlinear state-dependent terms. For such complex systems, deep neural networks can se…
Adaptive Machine Learning-Driven Multi-Fidelity Stratified Sampling for Failure Analysis of Nonlinear Stochastic Systems
Existing variance reduction techniques used in stochastic simulations for rare event analysis still require a substantial number of model evaluations to estimate small failure probabilities. In the context of complex, no…
Path Following and Stabilisation of a Bicycle Model using a Reinforcement Learning Approach
Over the years, complex control approaches have been developed to control the motion of a bicycle. Reinforcement Learning (RL), a branch of machine learning, promises easy deployment of so-called agents. Deployed agents …
Reinforcement Learning (RL)