A Machine with Short-Term, Episodic, and Semantic Memory Systems

1 code implementation • 5 Dec 2022 • Taewoon Kim, Michael Cochez, Vincent François-Lavet, Mark Neerincx, Piek Vossen

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph.

Q-Learning Reinforcement Learning (RL)

Disentangled (Un)Controllable Features

1 code implementation • 31 Oct 2022 • Jacob E. Kooi, Mark Hoogendoorn, Vincent François-Lavet

In the context of MDPs with high-dimensional states, downstream tasks are predominantly applied on a compressed, low-dimensional representation of the original input space.

reinforcement-learning Reinforcement Learning (RL) +1

A Meta-Reinforcement Learning Algorithm for Causal Discovery

1 code implementation • 18 Jul 2022 • Andreas Sauter, Erman Acar, Vincent François-Lavet

Causal discovery is a major task with the utmost importance for machine learning since causal structures can enable models to go beyond pure correlation-based inference and significantly boost their performance.

Causal Discovery Meta Reinforcement Learning +2

Domain Adversarial Reinforcement Learning

no code implementations • 14 Feb 2021 • Bonnie Li, Vincent François-Lavet, Thang Doan, Joelle Pineau

We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e. g. when there are different backgrounds or change in contrast, brightness, etc.

reinforcement-learning Reinforcement Learning (RL)

Novelty Search in Representational Space for Sample Efficient Exploration

1 code implementation • NeurIPS 2020 • Ruo Yu Tao, Vincent François-Lavet, Joelle Pineau

We then leverage these intrinsic rewards for sample-efficient exploration with planning routines in representational space for hard exploration tasks with sparse rewards.

Efficient Exploration

Neural Architecture Search for Class-incremental Learning

no code implementations • 14 Sep 2019 • Shenyang Huang, Vincent François-Lavet, Guillaume Rabusseau

To understand how to expand a continual learner, we focus on the neural architecture design problem in the context of class-incremental learning: at each time step, the learner must optimize its performance on all classes observed so far by selecting the most competitive neural architecture.

Class Incremental Learning Incremental Learning +1

Combined Reinforcement Learning via Abstract Representations

1 code implementation • 12 Sep 2018 • Vincent François-Lavet, Yoshua Bengio, Doina Precup, Joelle Pineau

In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages.

reinforcement-learning Reinforcement Learning (RL) +1

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies

no code implementations • 7 Dec 2015 • Vincent François-Lavet, Raphael Fonteneau, Damien Ernst

When the discount factor progressively increases up to its final value, we empirically show that it is possible to significantly reduce the number of learning steps.

reinforcement-learning Reinforcement Learning (RL)

Simple connectome inference from partial correlation statistics in calcium imaging

1 code implementation • 30 Jun 2014 • Antonio Sutera, Arnaud Joly, Vincent François-Lavet, Zixiao Aaron Qiu, Gilles Louppe, Damien Ernst, Pierre Geurts

In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data.