English
Related papers

Related papers: One controller to rule them all

200 papers

Large-scale foundation models for scientific machine learning adapt to physical settings unseen during training, such as zero-shot transfer between turbulent scales. This phenomenon, in-context learning, challenges conventional…

Machine Learning · Computer Science 2026-04-14 Anthony Bao , Jeffrey Lai , William Gilpin

We will show that there is a universal connection between the achievable closed-loop dynamics and the corresponding feedback controller that produces it. This connection shows promise to lead to new methods for robust nonlinear control in…

Systems and Control · Electrical Eng. & Systems 2020-04-20 Dimitar Ho

The abundance of process operating data in modern industries, along with the rapid advancement of learning techniques, has led to a paradigm shift towards data-centric analysis and control. However, integrating machine learning with control…

Systems and Control · Electrical Eng. & Systems 2026-04-16 Yitao Yan , Yu Tong , Jie Bao , Wei Wang

By extending the extreme learning machine by additional control inputs, we achieved almost complete reproduction of bifurcation structures of dynamical systems. The learning ability of the proposed neural network system is striking in that…

Chaotic Dynamics · Physics 2024-10-21 Satoru Tadokoro , Akihiro Yamaguchi , Takao Namiki , Ichiro Tsuda

We propose a hierarchical learning architecture for predictive control in unknown environments. We consider a constrained nonlinear dynamical system and assume the availability of state-input trajectories solving control tasks in different…

Systems and Control · Electrical Eng. & Systems 2020-07-16 Charlott Vallon , Francesco Borrelli

The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch…

At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto-regressive objectives is closely related to…

We introduce a unified Learning Context (LC) framework designed to transition AI-based education from context-blind mimicry to a principled, holistic understanding of the learner. This white paper provides a multidisciplinary roadmap for…

We propose a categorical framework for processes which interact bidirectionally with both an environment and a 'controller'. Examples include open learners, in which the controller is an optimiser such as gradient descent, and an approach…

Category Theory · Mathematics 2022-11-04 Matteo Capucci , Bruno Gavranović , Jules Hedges , Eigil Fjeldgren Rischel

This paper proposes a framework for adaptively learning a feedback linearization-based tracking controller for an unknown system using discrete-time model-free policy-gradient parameter update rules. The primary advantage of the scheme over…

Machine Learning · Computer Science 2020-04-07 Tyler Westenbroek , Eric Mazumdar , David Fridovich-Keil , Valmik Prabhu , Claire J. Tomlin , S. Shankar Sastry

Motivated by perception-based control problems in autonomous systems, this paper addresses the problem of developing feedback controllers to regulate the inputs and the states of a dynamical system to optimal solutions of an optimization…

Systems and Control · Electrical Eng. & Systems 2023-10-17 Liliaokeawawa Cothren , Gianluca Bianchin , Sarah Dean , Emiliano Dall'Anese

According to the principle of compositional generalization, the meaning of a complex expression can be understood as a function of the meaning of its parts and of how they are combined. This principle is crucial for human language…

Computation and Language · Computer Science 2024-03-19 Sungjun Han , Sebastian Padó

For controller design for systems on manifolds embedded in Euclidean space, it is convenient to utilize a theory that requires a single global coordinate system on the ambient Euclidean space rather than multiple local charts on the…

Optimization and Control · Mathematics 2019-10-15 Dong Eui Chang , Karmvir Singh Phogat , Jongeun Choi

While Reinforcement Learning ( RL) has made great strides towards solving increasingly complicated problems, many algorithms are still brittle to even slight environmental changes. Contextual Reinforcement Learning (cRL) provides a…

We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces. This provides one way of leveraging and combining the advantages of…

Machine Learning · Computer Science 2019-10-15 Brandon Amos , Ivan Dario Jimenez Rodriguez , Jacob Sacks , Byron Boots , J. Zico Kolter

This paper introduces a new mechanism for specifying constraints in distributed workflows. By introducing constraints in a contextual form, it is shown how different people and groups within collaborative communities can cooperatively…

Distributed, Parallel, and Cluster Computing · Computer Science 2007-05-23 G. E. Graham , M. Anzar Afaq , David Evans , Gerald Guglielmo , Eric Wicklund , Peter Love

Many realistic robotics tasks are best solved compositionally, through control architectures that sequentially invoke primitives and achieve error correction through the use of loops and conditionals taking the system back to alternative…

Robotics · Computer Science 2019-06-25 Daniel Angelov , Yordan Hristov , Subramanian Ramamoorthy

Dynamic software adaptability is one of the central features leveraged by autonomic computing. However, developing software that changes its behavior at run time adapting to the operational conditions is a challenging task. Several…

Programming Languages · Computer Science 2012-04-02 Guido Salvaneschi , Carlo Ghezzi , Matteo Pradella

Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key…

Machine Learning · Computer Science 2022-06-27 Matthieu Kirchmeyer , Yuan Yin , Jérémie Donà , Nicolas Baskiotis , Alain Rakotomamonjy , Patrick Gallinari

This paper proposes a robust control design method using reinforcement-learning for controlling partially-unknown dynamical systems under uncertain conditions. The method extends the optimal reinforcement-learning algorithm with a new…

Systems and Control · Electrical Eng. & Systems 2020-04-17 Phuong D. Ngo , Fred Godtliebsen