English
Related papers

Related papers: Simple Policy Evaluation for Data-Rich Iterative T…

200 papers

We propose and analyze a stabilizing iteration scheme for the algorithmic implementation of model predictive control for linear discrete-time systems. Polytopic input and state constraints are considered and handled by means of so-called…

Optimization and Control · Mathematics 2016-04-07 Christian Feller , Christian Ebenbauer

An information based method for solving stochastic control problems with partial observation has been proposed. First, the information-theoretic lower bounds of the cost function has been analysed. It has been shown, under rather weak…

Optimization and Control · Mathematics 2019-11-21 Piotr Bania

Data-Enabled Predictive Control (DeePC) has emerged as a powerful framework for controlling unknown systems directly from input-output data. For nonlinear systems, recent work has proposed selecting relevant subsets of data columns based on…

Systems and Control · Electrical Eng. & Systems 2026-03-26 Jiachen Li , Shihao Li , Jiamin Xu , Soovadeep Bakshi , Dongmei Chen

We propose novel iterative learning control algorithms to track a reference trajectory in resource-constrained control systems. In many applications, there are constraints on the number of control actions, delivered to the actuator from the…

Optimization and Control · Mathematics 2017-09-29 Burak Demirel , Euhanna Ghadimi , Daniel E. Quevedo

Robots executing iterative tasks in complex, uncertain environments require control strategies that balance robustness, safety, and high performance. This paper introduces a safe information-theoretic learning model predictive control…

We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of…

Machine Learning · Computer Science 2022-03-16 Safa Alver , Doina Precup

We develop a control algorithm that ensures the safety, in terms of confinement in a set, of a system with unknown, 2nd-order nonlinear dynamics. The algorithm establishes novel connections between data-driven and robust, nonlinear control.…

Systems and Control · Electrical Eng. & Systems 2021-05-17 Christos K. Verginis , Franck Djeumou , Ufuk Topcu

When a robotic system is redundant with respect to a given task, the remaining degrees of freedom can be used to satisfy additional objectives. With current robotic systems having more and more degrees of freedom, this can lead to an entire…

Robotics · Computer Science 2024-03-14 Gianluca Garofalo

In order to solve complex, long-horizon tasks, intelligent robots need to carry out high-level, abstract planning and reasoning in conjunction with motion planning. However, abstract models are typically lossy and plans or policies computed…

Robotics · Computer Science 2022-05-27 Naman Shah , Siddharth Srivastava

We consider challenging dynamic programming models where the associated Bellman equation, and the value and policy iteration algorithms commonly exhibit complex and even pathological behavior. Our analysis is based on the new notion of…

Optimization and Control · Mathematics 2016-09-13 Dimitri P. Bertsekas

Generalist robot policies that can perform many tasks typically require extensive expert data or simulations for training. In this work, we propose a novel Data-Efficient multitask DAgger framework that distills a single multitask policy…

Machine Learning · Computer Science 2025-10-01 Haotian Fu , Ran Gong , Xiaohan Zhang , Maria Vittoria Minniti , Jigarkumar Patel , Karl Schmeckpeper

We propose a data-driven online convex optimization algorithm for controlling dynamical systems. In particular, the control scheme makes use of an initially measured input-output trajectory and behavioral systems theory which enable it to…

Optimization and Control · Mathematics 2021-11-03 Marko Nonhoff , Matthias A. Müller

There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches. In this paper we attempt to evaluate this intuition on various challenging locomotion tasks. We take a…

Many potential applications of reinforcement learning (RL) are stymied by the large numbers of samples required to learn an effective policy. This is especially true when applying RL to real-world control tasks, e.g. in the sciences or…

Machine Learning · Computer Science 2022-10-11 Viraj Mehta , Ian Char , Joseph Abbate , Rory Conlin , Mark D. Boyer , Stefano Ermon , Jeff Schneider , Willie Neiswanger

In vehicular cloud computing (VCC) systems, the computational resources of moving vehicles are exploited and managed by infrastructures, e.g., roadside units, to provide computational services. The offloading of computational tasks and…

Information Theory · Computer Science 2017-12-01 Zhiyuan Jiang , Sheng Zhou , Xueying Guo , Zhisheng Niu

We consider the problem of discounted optimal state-feedback regulation for general unknown deterministic discrete-time systems. It is well known that open-loop instability of systems, non-quadratic cost functions and complex nonlinear…

Systems and Control · Electrical Eng. & Systems 2020-03-31 Alexandros Tanzanakis , John Lygeros

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

This paper presents a unified planning-control strategy for competing with other racing cars called IteraOptiRacing in autonomous racing environments. This unified strategy is proposed based on Iterative Linear Quadratic Regulator for…

Robotics · Computer Science 2025-07-15 Yifan Zeng , Yihan Li , Suiyi He , Koushil Sreenath , Jun Zeng

The imitation learning of self-driving vehicle policies through behavioral cloning is often carried out in an open-loop fashion, ignoring the effect of actions to future states. Training such policies purely with Empirical Risk Minimization…

Machine Learning · Computer Science 2022-10-12 Eesha Kumar , Yiming Zhang , Stefano Pini , Simon Stent , Ana Ferreira , Sergey Zagoruyko , Christian S. Perone

Many large MDPs can be represented compactly using a dynamic Bayesian network. Although the structure of the value function does not retain the structure of the process, recent work has shown that value functions in factored MDPs can often…

Artificial Intelligence · Computer Science 2013-01-18 Daphne Koller , Ron Parr