Search Results for author: Remi Tachet des Combes

Found 11 papers, 5 papers with code

Dr Jekyll & Mr Hyde: the strange case of off-policy policy updates

no code implementations NeurIPS 2021 Romain Laroche, Remi Tachet des Combes

To implement the principles prescribed by our theory, we propose an agent, Dr Jekyll & Mr Hyde (J&H), with a double personality: Dr Jekyll purely exploits while Mr Hyde purely explores.

On the Regularity of Attention

no code implementations10 Feb 2021 James Vuckovic, Aristide Baratin, Remi Tachet des Combes

Attention is a powerful component of modern neural networks across a wide variety of domains.

Decomposing Mutual Information for Representation Learning

no code implementations1 Jan 2021 Alessandro Sordoni, Nouha Dziri, Hannes Schulz, Geoff Gordon, Remi Tachet des Combes, Philip Bachman

In this paper, we transform each view into a set of subviews and then decompose the original MI bound into a sum of bounds involving conditional MI between the subviews.

Dialogue Generation Representation Learning

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

1 code implementation2 Oct 2020 Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes

In the second scenario, we consider optimizing a discounted objective ($\gamma < 1$) and propose to interpret the omission of the discounting in the actor update from an auxiliary task perspective and provide supporting empirical results.

Representation Learning

A Mathematical Theory of Attention

no code implementations6 Jul 2020 James Vuckovic, Aristide Baratin, Remi Tachet des Combes

Attention is a powerful component of modern neural networks across a wide variety of domains.

Deep Reinforcement and InfoMax Learning

1 code implementation NeurIPS 2020 Bogdan Mazoure, Remi Tachet des Combes, Thang Doan, Philip Bachman, R. Devon Hjelm

We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems.

Continual Learning

A Reduction from Reinforcement Learning to No-Regret Online Learning

no code implementations14 Nov 2019 Ching-An Cheng, Remi Tachet des Combes, Byron Boots, Geoff Gordon

We present a reduction from reinforcement learning (RL) to no-regret online learning based on the saddle-point formulation of RL, by which "any" online algorithm with sublinear regret can generate policies with provable performance guarantees.

online learning reinforcement-learning

On Learning Invariant Representation for Domain Adaptation

2 code implementations27 Jan 2019 Han Zhao, Remi Tachet des Combes, Kun Zhang, Geoffrey J. Gordon

Our result characterizes a fundamental tradeoff between learning invariant representations and achieving small joint error on both domains when the marginal label distributions differ from source to target.

Representation Learning Unsupervised Domain Adaptation

An Empirical Study of Example Forgetting during Deep Neural Network Learning

2 code implementations ICLR 2019 Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, Geoffrey J. Gordon

Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks.

General Classification

Convergence Properties of Deep Neural Networks on Separable Data

no code implementations27 Sep 2018 Remi Tachet des Combes, Mohammad Pezeshki, Samira Shabanian, Aaron Courville, Yoshua Bengio

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood.

Counting to Explore and Generalize in Text-based Games

2 code implementations29 Jun 2018 Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler

We propose a recurrent RL agent with an episodic exploration mechanism that helps discovering good policies in text-based game environments.

text-based games

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