English
Related papers

Related papers: Learning What Matters: Adaptive Information-Theore…

200 papers

In this work, we propose an attention-based deep reinforcement learning approach to address the adaptive informative path planning (IPP) problem in 3D space, where an aerial robot equipped with a downward-facing sensor must dynamically…

Robotics · Computer Science 2025-06-11 Rui Zhao , Xingjian Zhang , Yuhong Cao , Yizhuo Wang , Guillaume Sartoretti

We consider optimal experimental design (OED) problems in selecting the most informative observation sensors to estimate model parameters in a Bayesian framework. Such problems are computationally prohibitive when the…

Computational Engineering, Finance, and Science · Computer Science 2024-09-10 Jinwoo Go , Peng Chen

Conventional Bayesian optimal experimental design seeks to maximize the expected information gain (EIG) on model parameters. However, the end goal of the experiment often is not to learn the model parameters, but to predict downstream…

Computation · Statistics 2024-08-20 Atlanta Chakraborty , Xun Huan , Tommie Catanach

The core objective of machine-assisted scientific discovery is to learn physical laws from experimental data without prior knowledge of the systems in question. In the area of quantum physics, making progress towards these goals is…

Quantum Physics · Physics 2023-01-09 Matthew Choi , Daniel Flam-Shepherd , Thi Ha Kyaw , Alán Aspuru-Guzik

Efficient exploration remains a major challenge for reinforcement learning. One reason is that the variability of the returns often depends on the current state and action, and is therefore heteroscedastic. Classical exploration strategies…

Machine Learning · Computer Science 2019-03-26 Nikolay Nikolov , Johannes Kirschner , Felix Berkenkamp , Andreas Krause

Incomplete knowledge of the environment leads an agent to make decisions under uncertainty. One of the major dilemmas in Reinforcement Learning (RL) where an autonomous agent has to balance two contrasting needs in making its decisions is:…

Machine Learning · Statistics 2024-02-21 Valentina Zangirolami , Matteo Borrotti

Optimal experimental design (OED) seeks experiments expected to yield the most useful data for some purpose. In practical circumstances where experiments are time-consuming or resource-intensive, OED can yield enormous savings. We pursue…

Computation · Statistics 2014-12-30 Xun Huan , Youssef M. Marzouk

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Gianluca Scarpellini , Stefano Rosa , Pietro Morerio , Lorenzo Natale , Alessio Del Bue

We consider robust optimal experimental design (ROED) for nonlinear Bayesian inverse problems governed by partial differential equations (PDEs). An optimal design is one that maximizes some utility quantifying the quality of the solution of…

Numerical Analysis · Mathematics 2026-05-01 Abhijit Chowdhary , Ahmed Attia , Alen Alexanderian

This work pushes the boundaries of learning-based methods in autonomous robot exploration in terms of environmental scale and exploration efficiency. We present HEADER, an attention-based reinforcement learning approach with hierarchical…

Robotics · Computer Science 2025-10-20 Yuhong Cao , Yizhuo Wang , Jingsong Liang , Shuhao Liao , Yifeng Zhang , Peizhuo Li , Guillaume Sartoretti

The iterative search process of evolutionary algorithms (EAs) encapsulates optimization knowledge within historical populations and fitness evaluations. Effective utilization of this knowledge is crucial for facilitating knowledge transfer…

Neural and Evolutionary Computing · Computer Science 2026-04-22 Chao Wang , Lingling Li , Licheng Jiao , Jiaxuan Zhao , Fang Liu , Shuyuan Yang

In this paper, we investigate the utility of datasets and whether more data or the 'right' data is advantageous for robot learning. In particular, we are interested on quantifying the utility of contact-based data as contact holds…

Robotics · Computer Science 2025-10-22 Hrishikesh Sathyanarayan , Victor Vantilborgh , Ian Abraham

The field of quickest change detection (QCD) focuses on the design and analysis of online algorithms that estimate the time at which a significant event occurs. In this paper, design and analysis are cast in a Bayesian framework, where QCD…

Optimization and Control · Mathematics 2025-12-30 Austin Cooper , Sean Meyn

Quality-Diversity (QD) algorithms evolve behaviourally diverse and high-performing solutions. To illuminate the elite solutions for a space of behaviours, QD algorithms require the definition of a suitable behaviour space. If the behaviour…

Neural and Evolutionary Computing · Computer Science 2024-01-08 David M. Bossens , Danesh Tarapore

This paper introduces an innovative approach based on policy iteration (PI), a reinforcement learning (RL) algorithm, to obtain an optimal observer with a quadratic cost function. This observer is designed for systems with a given…

Systems and Control · Electrical Eng. & Systems 2023-11-29 Soroush Asri , Luis Rodrigues

Imitation learning has demonstrated impressive results in robotic manipulation but fails under out-of-distribution (OOD) states. This limitation is particularly critical in Deformable Object Manipulation (DOM), where the near-infinite…

Robotics · Computer Science 2026-03-17 Yujiro Onishi , Ryo Takizawa , Yoshiyuki Ohmura , Yasuo Kuniyoshi

Quality Diversity (QD) has shown great success in discovering high-performing, diverse policies for robot skill learning. While current benchmarks have led to the development of powerful QD methods, we argue that new paradigms must be…

Robotics · Computer Science 2024-07-26 Sumeet Batra , Bryon Tjanaka , Stefanos Nikolaidis , Gaurav Sukhatme

This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables…

Robotics · Computer Science 2020-12-08 Ian Abraham , Ahalya Prabhakar , Todd D. Murphey

Quadrupeds are strong candidates for navigating challenging environments because of their agile and dynamic designs. This paper presents a methodology that extends the range of exploration for quadrupedal robots by creating an end-to-end…

The objective of a reinforcement learning agent is to discover better actions through exploration. However, typical exploration techniques aim to maximize rewards, often incurring high costs in both exploration and learning processes. We…

Machine Learning · Computer Science 2024-12-24 Akane Tsuboya , Yu Kono , Tatsuji Takahashi