Identification and adaptive control of markov jump systems: Sample complexity and regret bounds
Learning how to effectively control unknown dynamical systems is crucial for intelligent
autonomous systems. This task becomes a significant challenge when the underlying …
autonomous systems. This task becomes a significant challenge when the underlying …
Data-driven control of markov jump systems: Sample complexity and regret bounds
Learning how to effectively control unknown dynamical systems from data is crucial for
intelligent autonomous systems. This task becomes a significant challenge when the …
intelligent autonomous systems. This task becomes a significant challenge when the …
A general framework for learning-based distributionally robust MPC of Markov jump systems
M Schuurmans, P Patrinos - IEEE Transactions on Automatic …, 2023 - ieeexplore.ieee.org
In this article, we present a data-driven learning model predictive control (MPC) scheme for
chance-constrained Markov jump systems with unknown switching probabilities. Using …
chance-constrained Markov jump systems with unknown switching probabilities. Using …
Policy learning of MDPs with mixed continuous/discrete variables: A case study on model-free control of Markovian jump systems
JP Jansch-Porto, B Hu… - Learning for Dynamics …, 2020 - proceedings.mlr.press
Markovian jump linear systems (MJLS) are an important class of dynamical systems that
arise in many control applications. In this paper, we introduce the problem of controlling …
arise in many control applications. In this paper, we introduce the problem of controlling …
Certainty equivalent quadratic control for markov jump systems
Real-world control applications often involve complex dynamics subject to abrupt changes
or variations. Markov jump linear systems (MJS) provide a rich framework for modeling such …
or variations. Markov jump linear systems (MJS) provide a rich framework for modeling such …
Thompson Sampling Achieves Regret in Linear Quadratic Control
Thompson Sampling (TS) is an efficient method for decision-making under uncertainty,
where an action is sampled from a carefully prescribed distribution which is updated based …
where an action is sampled from a carefully prescribed distribution which is updated based …
Learning-based stabilization of Markov jump linear systems
In this paper, we explore the stabilization problem of discrete-time Markov jump linear
systems from a new perspective. We establish a novel learning-based framework that …
systems from a new perspective. We establish a novel learning-based framework that …
Convergence guarantees of policy optimization methods for Markovian jump linear systems
JP Jansch-Porto, B Hu… - 2020 American Control …, 2020 - ieeexplore.ieee.org
Recently, policy optimization for control purposes has received renewed attention due to the
increasing interest in reinforcement learning. In this paper, we investigate the convergence …
increasing interest in reinforcement learning. In this paper, we investigate the convergence …
Regret lower bounds for learning linear quadratic gaussian systems
I Ziemann, H Sandberg - arXiv preprint arXiv:2201.01680, 2022 - arxiv.org
TWe establish regret lower bounds for adaptively controlling an unknown linear Gaussian
system with quadratic costs. We combine ideas from experiment design, estimation theory …
system with quadratic costs. We combine ideas from experiment design, estimation theory …
Data-driven distributionally robust control of partially observable jump linear systems
M Schuurmans, P Patrinos - 2021 60th IEEE Conference on …, 2021 - ieeexplore.ieee.org
We study data-driven control of (Markov) jump linear systems with unknown transition
probabilities, where both the discrete mode and the continuous state are to be inferred from …
probabilities, where both the discrete mode and the continuous state are to be inferred from …