Pablo Sprechmann — accepted AI-conference papers

2024

Unlocking the Power of Representations in Long-term Novelty-based Exploration

Alaa Saade, Steven Kapturowski, Daniele Calandriello, Charles Blundell, Pablo Sprechmann, Leopoldo Sarra +3

ICLR 2024spotlight

We introduce Robust Exploration via Clustering-based Online Density Estimation (RECODE), a non-parametric method for novelty-based exploration that estimates visitation counts for clusters of states based on their similarity in a chosen embedding space. By adapting classical clustering to the nonsta…

Cited by 6 Source ↗PDF ↗Scholar ↗

2020

Agent57: Outperforming the Atari Human Benchmark

Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Zhaohan Daniel Guo +1

ICML 2020poster

Atari games have been a long-standing benchmark in the reinforcement learning (RL) community for the past decade. This benchmark was proposed to test general competency of RL algorithms. Previous work has achieved good average performance by doing outstandingly well on many games of the set, but ver…

Cited by 759 Source ↗PDF ↗Scholar ↗

2020

Never Give Up: Learning Directed Exploration Strategies

Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Bilal Piot, Steven Kapturowski +5

ICLR 2020poster

We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby enco…

Cited by 410 Source ↗Scholar ↗

2018

Fast deep reinforcement learning using online adjustments from the past

Steven Hansen, Alexander Pritzel, Pablo Sprechmann, Andre Barreto, Charles Blundell

NeurIPS 2018poster

We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by prioritised sweeping over experience tuples fr…

Cited by 50 Source ↗PDF ↗code ↗Scholar ↗

2018

Memory-based Parameter Adaptation

Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adria Puigdomenech Badia, Benigno Uria +4

ICLR 2018poster

Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the training distribution shifts, the network is slow to adapt, an…

Cited by 121 Source ↗PDF ↗Scholar ↗

2017

Accelerating Eulerian Fluid Simulation With Convolutional Networks

Jonathan Tompson, Kristofer Schlachter, Pablo Sprechmann, Ken Perlin

ICML 2017poster

Efficient simulation of the Navier-Stokes equations for fluid flow is a long standing problem in applied mathematics, for which state-of-the-art methods require large compute resources. In this work, we propose a data-driven approach that leverages the approximation power of deep-learning with the p…

Cited by 741 Source ↗PDF ↗Scholar ↗

2016

Disentangling factors of variation in deep representation using adversarial training

Michael F Mathieu, Junbo Jake Zhao, Junbo Zhao, Aditya Ramesh, Pablo Sprechmann, Yann LeCun

NeurIPS 2016poster

We propose a deep generative model for learning to distill the hidden factors of variation within a set of labeled observations into two complementary codes. One code describes the factors of variation relevant to solving a specified task. The other code describes the remaining factors of variation…

Cited by 574 Source ↗PDF ↗Scholar ↗

2015

Source separation with scattering Non-Negative Matrix Factorization

Joan Bruna, Pablo Sprechmann, Yann LeCun

ICASSP 2015accepted

This paper presents a single-channel source separation method that extends the ideas of Nonnegative Matrix Factorization (NMF). We interpret the approach of audio demixing via NMF as a cascade of a pooled analysis operator, given for example by the magnitude spectrogram, and a synthesis operators gi…

Cited by 0 Source ↗Scholar ↗