Search Results for author: Vicenç Gómez

Found 16 papers, 8 papers with code

Beyond 1-WL with Local Ego-Network Encodings

1 code implementation27 Nov 2022 Nurudin Alvarez-Gonzalez, Andreas Kaltenbrunner, Vicenç Gómez

Identifying similar network structures is key to capture graph isomorphisms and learn representations that exploit structural information encoded in graph data.

Hierarchical Width-Based Planning and Learning

1 code implementation15 Jan 2021 Miquel Junyent, Vicenç Gómez, Anders Jonsson

In classical planning, we show how IW(1) at two levels of abstraction can solve problems of width 2.

Atari Games

Adaptive Smoothing Path Integral Control

no code implementations13 May 2020 Dominik Thalmeier, Hilbert J. Kappen, Simone Totaro, Vicenç Gómez

We identify PICE as the infinite smoothing limit of such technique and show that the sample efficiency problems that PICE suffers disappear for finite levels of smoothing.

Input complexity and out-of-distribution detection with likelihood-based generative models

2 code implementations ICLR 2020 Joan Serrà, David Álvarez, Vicenç Gómez, Olga Slizovskaia, José F. Núñez, Jordi Luque

Likelihood-based generative models are a promising resource to detect out-of-distribution (OOD) inputs which could compromise the robustness or reliability of a machine learning system.

Anomaly Detection OOD Detection +1

Consequential Ranking Algorithms and Long-term Welfare

no code implementations13 May 2019 Behzad Tabibian, Vicenç Gómez, Abir De, Bernhard Schölkopf, Manuel Gomez Rodriguez

Can we design ranking models that understand the consequences of their proposed rankings and, more importantly, are able to avoid the undesirable ones?

Misinformation

Deep Policies for Width-Based Planning in Pixel Domains

1 code implementation12 Apr 2019 Miquel Junyent, Anders Jonsson, Vicenç Gómez

Surprisingly, we observe that the representation learned by the neural network can be used as a feature space for the width-based planner without degrading its performance, thus removing the requirement of pre-defined features for the planner.

Atari Games

The few-get-richer: a surprising consequence of popularity-based rankings

no code implementations7 Feb 2019 Fabrizio Germano, Vicenç Gómez, Gaël Le Mens

Ranking algorithms play a crucial role in online platforms ranging from search engines to recommender systems.

Misinformation Recommendation Systems

Sharing emotions at scale: The Vent dataset

2 code implementations15 Jan 2019 Nikolaos Lykousas, Costantinos Patsakis, Andreas Kaltenbrunner, Vicenç Gómez

We present the Vent dataset, the largest annotated dataset of text, emotions, and social connections to date.

Social and Information Networks Human-Computer Interaction

Adult content in Social Live Streaming Services: Characterizing deviant users and relationships

1 code implementation27 Jun 2018 Nikolaos Lykousas, Vicenç Gómez, Constantinos Patsakis

Social Live Stream Services (SLSS) exploit a new level of social interaction.

Social and Information Networks

Improving width-based planning with compact policies

no code implementations15 Jun 2018 Miquel Junyent, Anders Jonsson, Vicenç Gómez

The planning step hinges on the Iterated-Width (IW) planner, a state of the art planner that makes explicit use of the state representation to perform structured exploration.

Atari Games reinforcement-learning

A unified view of entropy-regularized Markov decision processes

no code implementations22 May 2017 Gergely Neu, Anders Jonsson, Vicenç Gómez

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs).

Policy Gradient Methods reinforcement-learning

Fast rates for online learning in Linearly Solvable Markov Decision Processes

no code implementations21 Feb 2017 Gergely Neu, Vicenç Gómez

We study the problem of online learning in a class of Markov decision processes known as linearly solvable MDPs.

online learning

Hierarchical Linearly-Solvable Markov Decision Problems

no code implementations10 Mar 2016 Anders Jonsson, Vicenç Gómez

We present a hierarchical reinforcement learning framework that formulates each task in the hierarchy as a special type of Markov decision process for which the Bellman equation is linear and has analytical solution.

Hierarchical Reinforcement Learning reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.