141 citations · 638 across the 52 of their papers we have counts for
12 papers · 1 filter
Functional Risk Minimization
Ferran Alet, Clement Gehring, Tomás Lozano-Pérez +3
The field of Machine Learning has changed significantly since the 1970s. However, its most basic principle, Empirical Risk Minimization (ERM), remains unchanged. We propose Functio…
Neural Relational Inference with Fast Modular Meta-learning
Ferran Alet, Erica Weng, Tomás Lozano Pérez +1
\textit{Graph neural networks} (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of e…
Learning Object-Based State Estimators for Household Robots
Yilun Du, Tomas Lozano-Perez, Leslie Kaelbling
A robot operating in a household makes observations of multiple objects as it moves around over the course of days or weeks. The objects may be moved by inhabitants, but not comple…
Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
Ferran Alet, Maria Bauza, Kenji Kawaguchi +3
From CNNs to attention mechanisms, encoding inductive biases into neural networks has been a fruitful source of improvement in machine learning. Adding auxiliary losses to the main…
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
Tom Silver, Rohan Chitnis, Aidan Curtis +3
Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to pr…
CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs
Rohan Chitnis, Tom Silver, Beomjoon Kim +2
Meta-planning, or learning to guide planning from experience, is a promising approach to improving the computational cost of planning. A general meta-planning strategy is to learn…
Meta-learning curiosity algorithms
Ferran Alet, Martin F. Schneider, Tomas Lozano-Perez +1
We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it…
Learning Compact Models for Planning with Exogenous Processes
Rohan Chitnis, Tomás Lozano-Pérez
We address the problem of approximate model minimization for MDPs in which the state is partitioned into endogenous and (much larger) exogenous components. An exogenous state varia…
Differentiable Algorithm Networks for Composable Robot Learning
Peter Karkus, Xiao Ma, David Hsu +3
This paper introduces the Differentiable Algorithm Network (DAN), a composable architecture for robot learning systems. A DAN is composed of neural network modules, each encoding a…
Graph Element Networks: adaptive, structured computation and memory
Ferran Alet, Adarsh K. Jeewajee, Maria Bauza +3
We explore the use of graph neural networks (GNNs) to model spatial processes in which there is no a priori graphical structure. Similar to finite element analysis, we assign nodes…
Modular meta-learning in abstract graph networks for combinatorial generalization
Ferran Alet, Maria Bauza, Alberto Rodriguez +2
Modular meta-learning is a new framework that generalizes to unseen datasets by combining a small set of neural modules in different ways. In this work we propose abstract graph ne…
Modular meta-learning
Ferran Alet, Tomás Lozano-Pérez, Leslie P. Kaelbling
Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we…