The scenario approach: A tool at the service of data-driven decision making
In the eyes of many control scientists, the theory of the scenario approach is a tool for
determining the sample size in certain randomized control-design methods, where an …
determining the sample size in certain randomized control-design methods, where an …
Deepreach: A deep learning approach to high-dimensional reachability
Hamilton-Jacobi (HJ) reachability analysis is an important formal verification method for
guaranteeing performance and safety properties of dynamical control systems. Its …
guaranteeing performance and safety properties of dynamical control systems. Its …
Proximal point imitation learning
This work develops new algorithms with rigorous efficiency guarantees for infinite horizon
imitation learning (IL) with linear function approximation without restrictive coherence …
imitation learning (IL) with linear function approximation without restrictive coherence …
Data-driven optimal control of affine systems: A linear programming perspective
A Martinelli, M Gargiani, M Draskovic… - IEEE Control Systems …, 2022 - ieeexplore.ieee.org
In this letter, we discuss the problem of optimal control for affine systems in the context of
data-driven linear programming. First, we introduce a unified framework for the fixed point …
data-driven linear programming. First, we introduce a unified framework for the fixed point …
Data-driven optimal control via linear programming: boundedness guarantees
The linear programming (LP) approach is, together with value iteration and policy iteration,
one of the three fundamental methods to solve optimal control problems in a dynamic …
one of the three fundamental methods to solve optimal control problems in a dynamic …
[HTML][HTML] Data-driven optimal control with a relaxed linear program
The linear programming (LP) approach has a long history in the theory of approximate
dynamic programming. When it comes to computation, however, the LP approach often …
dynamic programming. When it comes to computation, however, the LP approach often …
Efficient performance bounds for primal-dual reinforcement learning from demonstrations
A Kamoutsi, G Banjac… - … Conference on Machine …, 2021 - proceedings.mlr.press
We consider large-scale Markov decision processes with an unknown cost function and
address the problem of learning a policy from a finite set of expert demonstrations. We …
address the problem of learning a policy from a finite set of expert demonstrations. We …
A data-driven policy iteration scheme based on linear programming
We consider the problem of learning discounted-cost optimal control policies for unknown
deterministic discrete-time systems with continuous state and action spaces. We show that a …
deterministic discrete-time systems with continuous state and action spaces. We show that a …
Reachability Analysis for Black-Box Dynamical Systems
VK Chilakamarri, Z Feng, S Bansal - arXiv preprint arXiv:2410.07796, 2024 - arxiv.org
Hamilton-Jacobi (HJ) reachability analysis is a powerful framework for ensuring safety and
performance in autonomous systems. However, existing methods typically rely on a white …
performance in autonomous systems. However, existing methods typically rely on a white …
On the synthesis of Bellman inequalities for data-driven optimal control
A Martinelli, M Gargiani… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
In the context of the linear programming (LP) approach to data-driven control, one assumes
that the dynamical system is unknown but can be observed indirectly through data on its …
that the dynamical system is unknown but can be observed indirectly through data on its …