Publications related to Learning Search Strategies from Human Demonstrations

Related publications (47)

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

EPFL2025

Exact Obstacle Avoidance for Robots in Complex and Dynamic Environments Using Local Modulation

Lukas Huber

Robots outside of the fenced factories have to deal with continuously changing environment, this requires fast and flexible modes of control. Planning methods or complex learning models can find optimal paths in complex surroundings, but they are computati ...

EPFL2024

Sense in Motion with Belief Clustering: Efficient Gas Source Localization with Mobile Robots

Alcherio Martinoli, Wanting Jin

Given the patchy nature of gas plumes and the slow response of conventional gas sensors, the use of mobile robots for Gas Source Localization (GSL) tasks presents significant challenges. These aspects increase the difficulties in obtaining gas measurements ...

2024

Learning to Assemble with Alternative Plans

Gabriel Rémi Vallat, Maryam Kamgarpour, Stefana Parascho, Ziqi Wang, Jingwen Wang

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

Association for Computing Machinery (ACM)2025

Self-supervised and few-shot learning for robust bioaerosol monitoring

Sophie Catherine Erb

Real-time bioaerosol monitoring is improving the quality of life for people affected by allergies, but it often relies on deep learning models which pose challenges for widespread adoption. These models are typically trained in a supervised fashion and req ...

2025

Extensions of Peer Prediction Incentive Mechanisms

Adam Julian Richardson

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

EPFL2024

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Liza Carol Andrea Dunbar

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

IOP Publishing Ltd2025

Robot Learning using Tensor Networks

Suhan Narayana Shetty

In various robotics applications, the selection of function approximation methods greatly influences the feasibility and computational efficiency of algorithms. Tensor Networks (TNs), also referred to as tensor decomposition techniques, present a versatile ...

EPFL2024

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression

Mathieu Salzmann, Alexandre Massoud Alahi, Megh Hiren Shukla

Deep heteroscedastic regression models the mean and covariance of the target distribution through neural networks. The challenge arises from heteroscedasticity, which implies that the covariance is sample dependent and is often unknown. Consequently, recen ...

ICLR2025

Online Multicontact Receding Horizon Planning via Value Function Approximation

Sylvain Calinon, Teguh Santoso Lembono

Planning multicontact motions in a receding horizon fashion requires a value function to guide the planning with respect to the future, e.g., building momentum to traverse large obstacles. Traditionally, the value function is approximated by computing traj ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Context selectivity with dynamic availability enables lifelong continual learning

Wulfram Gerstner, Guillaume Emmanuel Fernand Bellec, Martin Louis Lucien Rémy Barry

“You never forget how to ride a bike”, – but how is that possible? The brain is able to learn complex skills, stop the practice for years, learn other skills in between, and still retrieve the original knowledge when necessary. The mechanisms of this capab ...

Elsevier BV2025

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Mattia Atzeni

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

EPFL2024

Domain shift, domain adaptation, and generalization: A focus on MRI

Tobias Kober, Meritxell Bach Cuadra, Veronica Lily Ravano, Jonas Richiardi

Differences in acquisition protocols or hardware result in measurable changes in image characteristics. These differences affect distributional properties and can also affect the spatial and temporal characteristics of the images. Likewise, the distributio ...

Academic Press2025

Unveiling the complexity of learning and decision-making

Wei-Hsiang Lin

Reinforcement learning (RL) is crucial for learning to adapt to new environments. In RL, the prediction error is an important component that compares the expected and actual rewards. Dopamine plays a critical role in encoding these prediction errors. In my ...

EPFL2024

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Zaffar Ahmed Shaikh

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

SAGE PUBLICATIONS LTD2025

Social Opinion Formation and Decision Making Under Communication Trends

Ali H. Sayed, Virginia Bordignon, Mert Kayaalp

This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief information with each other while trying to infer the true state of nature. We stud ...

Ieee-Inst Electrical Electronics Engineers Inc2024

A phase transition between positional and semantic learning in a solvable model of dot-product attention

Lenka Zdeborová, Florent Gérard Krzakala, Hugo Chao Cui, Freya Behrens

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements in the model capabilities. Yet, a theoretical characterization of how such mecha ...

2025

Memento Mori: Reliable robustness in self-reconfigurable modular robots

Kevin Andrew Holdcroft

Modular robotics link the reliability of a centralised system with the adaptivity of a decentralised system. It is difficult for a robot with a fixed shape to be able to perform many different types of tasks. As the task space grows, the number of functi ...

EPFL2024

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Volkan Cevher, Fanghui Liu, Zhenyu Zhu

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

2025

Reactive collision-free motion generation in joint space via dynamical systems and sampling-based MPC

Aude Billard, Nadia Barbara Figueroa Fernandez, Mikhail Koptev

Dynamical system (DS) based motion planning offers collision-free motion, with closed-loop reactivity thanks to their analytical expression. It ensures that obstacles are not penetrated by reshaping a nominal DS through matrix modulation, which is construc ...

Sage Publications Ltd2024