10 citations · 47 across the 17 of their papers we have counts for
20 papers
Ground-Truth-First Benchmarking of Reinforcement Learning via Converse Optimality: From Smooth, Fully Observed Systems to Non-Smooth or Partially Observed Tasks
Grégoire Ouerdane, Sinan Ibrahim, Stefan Streif +1
Benchmarking in reinforcement learning is usually relative: algorithms are ranked by returns on environments with unknown optima. Distance to optimality remains unobservable, while…
Some Essential Constructive Foundations for Systems and Control
Pavel Osinenko
This work develops several constructive foundations for systems and control within Bishop-style constructive mathematics. For an engineer, the guiding principle is that an object c…
An Agency-Transferring Model-Free Policy Enhancement Technique
Anton Bolychev, Georgiy Malaniya, Sinan Ibrahim +1
Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation. Yet many con…
Benchmarking Reinforcement Learning via Stochastic Converse Optimality: Generating Systems with Known Optimal Policies
Sinan Ibrahim, Grégoire Ouerdane, Hadi Salloum +3
The objective comparison of Reinforcement Learning (RL) algorithms is notoriously complex as outcomes and benchmarking of performances of different RL approaches are critically sen…
Some remarks on robustness of sample-and-hold stabilization
Patrick Schmidt, Pavel Osinenko, Stefan Streif
This work studies robustness to system disturbance and measurement noise of some popular general practical stabilization techniques, namely, Dini aiming, optimization-based stabili…
Some remarks on practical stabilization via CLF-based control under measurement noise
Patrick Schmidt, Pavel Osinenko, Stefan Streif
Practical stabilization of input-affine systems in the presence of measurement errors and input constraints is considered in this brief note. Assuming that a Lyapunov function and…
Towards a constructive framework for control theory
Pavel Osinenko
This work presents a framework for control theory based on constructive analysis to account for discrepancy between mathematical results and their implementation in a computer, als…
On constructive extractability of measurable selectors of set-valued maps
Pavel Osinenko, Stefan Streif
This paper investigates the possibility of constructive extraction of measurable selector from set-valued maps which may commonly arise in viability theory, optimal control, discon…
Experimental verification of an online traction parameter identification method
Alexander Kobelski, Pavel Osinenko, Stefan Streif
Traction parameters, that characterize the ground-wheel contact dynamics, are the central factor in the energy efficiency of vehicles. To optimize fuel consumption, reduce wear of…
Optimal control of centrifugal spreader
Franz Rußwurm, Pavel Osinenko, Stefan Streif
Achieving an evenly distributed fertilization spread pattern is a complex technical task. A corresponding control algorithm must account for the tractor movement, the settings of t…
On inf-convolution-based robust practical stabilization under computational uncertainty
Patrick Schmidt, Pavel Osinenko, Stefan Streif
This work is concerned with practical stabilization of nonlinear systems by means of inf-convolution-based sample-and-hold control. It is a fairly general stabilization technique b…
Stacked adaptive dynamic programming with unknown system model
Pavel Osinenko, Thomas Göhrt, Grigory Devadze +1
Adaptive dynamic programming is a collective term for a variety of approaches to infinite-horizon optimal control. Common to all approaches is approximation of the infinite-horizon…
Nonsmooth stabilization and its computational aspects
Pavel Osinenko, Patrick Schmidt, Stefan Streif
This work has the goal of briefly surveying some key stabilization techniques for general nonlinear systems, for which, as it is well known, a smooth control Lyapunov function may…
A reinforcement learning method with closed-loop stability guarantee
Pavel Osinenko, Lukas Beckenbach, Thomas Göhrt +1
Reinforcement learning (RL) in the context of control systems offers wide possibilities of controller adaptation. Given an infinite-horizon cost function, the so-called critic of R…
A method of online traction parameter identification and mapping
Alexander Kobelski, Pavel Osinenko, Stefan Streif
Fuel consumption of heavy-duty vehicles such as tractors, bulldozers etc. is comparably high due to their scope of operation. The operation settings are usually fixed and not tuned…
Model predictive control with stage cost shaping inspired by reinforcement learning
Lukas Beckenbach, Pavel Osinenko, Stefan Streif
This work presents a suboptimality study of a particular model predictive control with a stage cost shaping based on the ideas of reinforcement learning. The focus of the suboptima…
Practical sample-and-hold stabilization of nonlinear systems under approximate optimizers
Pavel Osinenko, Lukas Beckenbach, Stefan Streif
It is a known fact that not all controllable systems can be asymptotically stabilized by a continuous static feedback. Several approaches have been developed throughout the last de…
Analysis of extremum value theorems for function spaces in optimal control under numerical uncertainty
Pavel Osinenko, Stefan Streif
The extremum value theorem for function spaces plays the central role in optimal control. It is known that computation of optimal control actions and policies is often prone to num…
A note on Brehm's extension theorem
Pavel Osinenko
Brehm's extension theorem states that a non-expansive map on a finite subset of a Euclidean space can be extended to a piecewise-linear map on the entire space. In this note, it is…
A note on constructive treatment of eigenvectors
Pavel Osinenko, Grigory Devadze, Stefan Streif
The eigenvalue problem plays a central role in linear algebra and its applications in control and optimization methods. In particular, many matrix decompositions rely upon computat…