English
Related papers

Related papers: Decision Transformer as a Foundation Model for Par…

200 papers

Despite the recent advancements in offline reinforcement learning via supervised learning (RvS) and the success of the decision transformer (DT) architecture in various domains, DTs have fallen short in several challenging benchmarks. The…

Machine Learning · Computer Science 2023-11-21 Anirudhan Badrinath , Yannis Flet-Berliac , Allen Nie , Emma Brunskill

The paper develops the Adaptive Dynamic Programming Toolbox (ADPT), which solves optimal control problems for continuous-time nonlinear systems. Based on the adaptive dynamic programming technique, the ADPT computes optimal feedback…

Optimization and Control · Mathematics 2021-01-01 Xiaowei Xing , Dong Eui Chang

Commonly adopted in the manufacturing and aerospace sectors, digital twin (DT) platforms are increasingly seen as a promising paradigm to control and monitor software-based, "open", communication systems, which play the role of the physical…

Signal Processing · Electrical Eng. & Systems 2023-01-30 Clement Ruah , Osvaldo Simeone , Bashir Al-Hashimi

With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well…

Computation and Language · Computer Science 2020-03-04 Qian Chen , Mengzhe Chen , Bo Li , Wen Wang

In recent years, extensive work has explored the application of the Transformer architecture to reinforcement learning problems. Among these, Decision Transformer (DT) has gained particular attention in the context of offline reinforcement…

Artificial Intelligence · Computer Science 2025-07-15 Yumi Omori , Zixuan Dong , Keith Ross

Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the action distribution based on target returns for each state in a…

Machine Learning · Computer Science 2023-12-22 Yuanfu Wang , Chao Yang , Ying Wen , Yu Liu , Yu Qiao

Notifications are an important communication channel for delivering timely and relevant information. Optimizing their delivery involves addressing complex sequential decision-making challenges under constraints such as message utility and…

Multi-object tracking (MOT) is the problem of tracking the state of an unknown and time-varying number of objects using noisy measurements, with important applications such as autonomous driving, tracking animal behavior, defense systems,…

Machine Learning · Computer Science 2022-02-17 Juliano Pinto , Georg Hess , William Ljungbergh , Yuxuan Xia , Henk Wymeersch , Lennart Svensson

The ability to adapt to changes in environmental contingencies is an important challenge in reinforcement learning. Indeed, transferring previously acquired knowledge to environments with unseen structural properties can greatly enhance the…

Machine Learning · Computer Science 2021-10-28 Ayman Boustati , Hana Chockler , Daniel C. McNamee

This work primarily focuses on an operator inference methodology aimed at constructing low-dimensional dynamical models based on a priori hypotheses about their structure, often informed by established physics or expert insights. Stability…

Machine Learning · Computer Science 2024-03-04 Igor Pontes Duff , Pawan Goyal , Peter Benner

We propose a data-driven control method for systems with aleatoric uncertainty, for example, robot fleets with variations between agents. Our method leverages shared trajectory data to increase the robustness of the designed controller and…

Robotics · Computer Science 2024-03-25 Alexander von Rohr , Dmitrii Likhachev , Sebastian Trimpe

Experimental design in field robotics is an adaptive human-in-the-loop decision-making process in which an experimenter learns about system performance and limitations through interactions with a robot in the form of constructed…

Robotics · Computer Science 2022-10-18 Jason M. Gregory , Sarah Al-Hussaini , Ali-akbar Agha-mohammadi , Satyandra K. Gupta

Classic control techniques typically rely on a model of the system's response to external inputs, which is difficult to obtain from first principles especially if the unknown dynamics are nonlinear. In this paper, we address this issue by…

Systems and Control · Electrical Eng. & Systems 2025-04-28 Anna Scampicchio , Melanie N. Zeilinger

Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based…

Machine Learning · Statistics 2019-12-24 Wonjae Kim , Yoonho Lee

Newton-Raphson controller is a powerful prediction-based variable gain integral controller. Basically, the classical model-based Newton-Raphson controller requires two elements: the prediction of the system output and the derivative of the…

Systems and Control · Electrical Eng. & Systems 2023-10-02 Mi Zhou

A drone trajectory planner should be able to dynamically adjust the safety-efficiency trade-off according to varying mission requirements in unknown environments. Although traditional polynomial-based planners offer computational efficiency…

Robotics · Computer Science 2025-07-31 Chang-Hun Ji , SiWoon Song , Youn-Hee Han , SungTae Moon

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing…

Machine Learning · Computer Science 2022-11-23 Anand Gopalakrishnan , Kazuki Irie , Jürgen Schmidhuber , Sjoerd van Steenkiste

We consider the problem of spatial path planning. In contrast to the classical solutions which optimize a new plan from scratch and assume access to the full map with ground truth obstacle locations, we learn a planner from the data in a…

Machine Learning · Computer Science 2021-12-03 Devendra Singh Chaplot , Deepak Pathak , Jitendra Malik

As a robot senses and selects actions, the world keeps changing. This inference delay creates a gap of tens to hundreds of milliseconds between the observed state and the state at execution. In this work, we take the natural generalization…

Robotics · Computer Science 2026-03-25 Aileen Liao , Dong-Ki Kim , Max Olan Smith , Ali-akbar Agha-mohammadi , Shayegan Omidshafiei

Today's focus on expanding the capabilities of control systems, resulting from the abundance of data and computational resources, requires data-based alternatives over model-based ones. These alternatives may become the sole tool for…

Systems and Control · Electrical Eng. & Systems 2024-06-06 Mostafa Eslami , Afshin Banazadeh