English
Related papers

Related papers: Learning Objective Functions Incrementally by Inve…

200 papers

We consider the problem of recovering an expert's reward function with inverse reinforcement learning (IRL) when there are missing/incomplete state-action pairs or observations in the demonstrated trajectories. This issue of missing…

Machine Learning · Computer Science 2019-11-19 Tien Mai , Quoc Phong Nguyen , Kian Hsiang Low , Patrick Jaillet

The goal of Inverse Optimal Control (IOC) is to identify the underlying objective function based on observed optimal trajectories. It provides a powerful framework to model expert's behavior, and a data-driven way to design an objective…

Optimization and Control · Mathematics 2022-04-28 Han Zhang , Axel Ringh , Weihan Jiang , Shaoyuan Li , Xiaoming Hu

Model-based reinforcement learning attempts to use an available or learned model to improve the data efficiency of reinforcement learning. This work proposes a one-step lookback approach that jointly learns the deep incremental model and…

Robotics · Computer Science 2025-02-28 Cong Li

Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a…

Machine Learning · Computer Science 2017-11-28 Peter Henderson , Wei-Di Chang , Pierre-Luc Bacon , David Meger , Joelle Pineau , Doina Precup

We present an approach to learn an object-centric forward model, and show that this allows us to plan for sequences of actions to achieve distant desired goals. We propose to model a scene as a collection of objects, each with an explicit…

Computer Vision and Pattern Recognition · Computer Science 2019-10-09 Yufei Ye , Dhiraj Gandhi , Abhinav Gupta , Shubham Tulsiani

Fast and precise motion control is important for industrial robots in manufacturing applications. However, some collaborative robots sacrifice precision for safety, particular for high motion speed. The performance degradation is caused by…

Robotics · Computer Science 2019-08-12 Shuyang Chen , John T. Wen

Non-prehensile pushing to move and reorient objects to a goal is a versatile loco-manipulation skill. In the real world, the object's physical properties and friction with the floor contain significant uncertainties, which makes the task…

Robotics · Computer Science 2025-10-22 Ioannis Dadiotis , Mayank Mittal , Nikos Tsagarakis , Marco Hutter

We present an end-to-end framework for generating solutions to combinatorial optimization problems with unknown components using transformer-based sequence-to-sequence neural networks. Our framework learns directly from past solutions and…

Optimization and Control · Mathematics 2026-02-06 Macarena Navarro , Willem-Jan van Hoeve , Karan Singh

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…

Robotics · Computer Science 2020-06-17 Marvin Chancán , Michael Milford

This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of…

Systems and Control · Electrical Eng. & Systems 2023-12-25 Prakash Mallick , Zhiyong Chen

Inverse reinforcement learning (IRL) seeks to learn the reward function from expert trajectories, to understand the task for imitation or collaboration thereby removing the need for manual reward engineering. However, IRL in the context of…

Machine Learning · Computer Science 2023-11-13 Yikang Gui , Prashant Doshi

It is doubtful that animals have perfect inverse models of their limbs (e.g., what muscle contraction must be applied to every joint to reach a particular location in space). However, in robot control, moving an arm's end-effector to a…

Robotics · Computer Science 2022-09-19 Justus Huebotter , Serge Thill , Marcel van Gerven , Pablo Lanillos

We present a robot eye-hand coordination learning method that can directly learn visual task specification by watching human demonstrations. Task specification is represented as a task function, which is learned using inverse reinforcement…

Robotics · Computer Science 2020-11-20 Jun Jin , Laura Petrich , Masood Dehghan , Zichen Zhang , Martin Jagersand

An iterative learning algorithm is presented for continuous-time linear-quadratic optimal control problems where the system is externally symmetric with unknown dynamics. Both finite-horizon and infinite-horizon problems are considered. It…

Optimization and Control · Mathematics 2025-10-10 Hamed Taghavian , Florian Dorfler , Mikael Johansson

Multi-Objective Learning Model Predictive Control is a novel data-driven control scheme which improves a linear system's closed-loop performance with respect to several convex control objectives over iterations of a repeated task. At each…

Systems and Control · Electrical Eng. & Systems 2024-10-21 Siddharth H. Nair , Charlott Vallon , Francesco Borrelli

Highly dynamic tasks that require large accelerations and precise tracking usually rely on accurate models and/or high gain feedback. While kinematic optimization allows for efficient representation and online generation of hitting…

Robotics · Computer Science 2019-03-19 Okan Koc , Guilherme Maeda , Jan Peters

In tasks such as surveying or monitoring remote regions, an autonomous robot must move while transmitting data over a wireless network with unknown, position-dependent transmission rates. For such a robot, this paper considers the problem…

Robotics · Computer Science 2020-11-19 L. Busoniu , V. S. Varma , J. Loheac , A. Codrean , O. Stefan , I. -C. Morarescu , S. Lasaulce

Underactuated systems like sea vessels have degrees of motion that are insufficiently matched by a set of independent actuation forces. In addition, the underlying trajectory-tracking control problems grow in complexity in order to decide…

Systems and Control · Electrical Eng. & Systems 2021-04-02 Mohammed Abouheaf , Wail Gueaieb , Md. Suruz Miah , Davide Spinello

We consider the problem of performing inverse reinforcement learning when the trajectory of the expert is not perfectly observed by the learner. Instead, a noisy continuous-time observation of the trajectory is provided to the learner. This…

Robotics · Computer Science 2017-10-30 Shervin Shahryari , Prashant Doshi

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the…

Machine Learning · Computer Science 2020-11-19 Saurabh Arora , Prashant Doshi , Bikramjit Banerjee