b'Damien Ernst'

DeepAI

Featured Co-authors

Sébastien Bubeck
52 publications
Gilles Louppe
44 publications
Aurélien Garivier
34 publications
Decebal Constantin Mocanu
33 publications
Vincent Francois-Lavet
18 publications
Pierre Geurts
17 publications
Louis Wehenkel
14 publications
Patrick Panciatici
12 publications
Matthia Sabatelli
11 publications
Arnaud Joly
10 publications
Elena Mocanu
10 publications

research

∙ 12/30/2022

Risk-Sensitive Policy with Distributional Reinforcement Learning

Classical reinforcement learning (RL) techniques are generally concerned...

Thibaut Théate, et al. ∙

research

∙ 11/21/2022

Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition

In this paper, we identify the best learning scenario to train a team of...

Pascal Leroy, et al. ∙

research

∙ 08/06/2022

Recurrent networks, hidden states and beliefs in partially observable environments

Reinforcement learning aims to learn optimal policies from interaction w...

Gaspard Lambrechts, et al. ∙

research

∙ 07/08/2022

Optimal Connection Phase Selection of Residential Distributed Energy Resources and its Impact on Aggregated Demand

The recent major increase in decentralized energy resources (DERs) such ...

Amina Benzerga, et al. ∙

research

∙ 01/07/2022

Churn prediction in online gambling

In business retention, churn prevention has always been a major concern....

Florian Merchie, et al. ∙

research

∙ 06/06/2021

Distributional Reinforcement Learning with Unconstrained Monotonic Neural Networks

The distributional reinforcement learning (RL) approach advocates for re...

Thibaut Théate, et al. ∙

research

∙ 06/02/2021

Warming-up recurrent neural networks to maximize reachable multi-stability greatly improves learning

Training recurrent neural networks is known to be difficult when time de...

Nicolas Vecoven, et al. ∙

research

∙ 05/20/2021

M4Depth: A motion-based approach for monocular depth estimation on video sequences

Getting the distance to objects is crucial for autonomous vehicles. In i...

Michaël Fonder, et al. ∙

research

∙ 05/18/2021

Gym-ANM: Open-source software to leverage reinforcement learning for power system management in research and education

Gym-ANM is a Python package that facilitates the design of reinforcement...

Robin Henry, et al. ∙

research

∙ 03/14/2021

Gym-ANM: Reinforcement Learning Environments for Active Network Management Tasks in Electricity Distribution Systems

Active network management (ANM) of electricity distribution networks inc...

Robin Henry, et al. ∙

research

∙ 03/02/2021

Sparse Training Theory for Scalable and Efficient Agents

A fundamental task for artificial intelligence is learning. Deep Neural ...

Decebal Constantin Mocanu, et al. ∙

research

∙ 02/22/2021

Remote Renewable Hubs For Carbon-Neutral Synthetic Fuel Production

This paper studies the economics of carbon-neutral synthetic fuel produc...

Mathias Berger, et al. ∙

research

∙ 12/22/2020

QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning

This paper introduces four new algorithms that can be used for tackling ...

Pascal Leroy, et al. ∙

research

∙ 09/09/2020

Allocation of locally generated electricity in renewable energy communities

This paper introduces a methodology to perform an ex-post allocation of ...

Miguel Manuel de Villena, et al. ∙

research

∙ 06/10/2020

An Artificial Intelligence Solution for Electricity Procurement in Forward Markets

Retailers and major consumers of electricity generally purchase a critic...

Thibaut Théate, et al. ∙

research

∙ 06/09/2020

A bio-inspired bistable recurrent cell allows for long-lasting memory

Recurrent neural networks (RNNs) provide state-of-the-art performances i...

Nicolas Vecoven, et al. ∙

research

∙ 06/02/2020

Learning optimal environments using projected stochastic gradient ascent

In this work, we generalize the direct policy search algorithms to an al...

Adrien Bolland, et al. ∙

research

∙ 04/13/2020

A Deep Reinforcement Learning Framework for Continuous Intraday Market Bidding

The large integration of variable energy resources is expected to shift ...

Ioannis Boukas, et al. ∙

research

∙ 04/07/2020

An Application of Deep Reinforcement Learning to Algorithmic Trading

This scientific research paper presents an innovative approach based on ...

Thibaut Théate, et al. ∙

research

∙ 12/21/2018

Introducing Neuromodulation in Deep Neural Networks to Learn Adaptive Behaviours

In this paper, we propose a new deep neural network architecture, called...

Nicolas Vecoven, et al. ∙

research

∙ 12/05/2018

Critical Time Windows for Renewable Resource Complementarity Assessment

This paper proposes a systematic framework to assess the complementarity...

Mathias Berger, et al. ∙

research

∙ 12/05/2018

Complementarity Assessment of South Greenland Katabatic Flows and West Europe Wind Regimes

Current global environmental challenges require firm, yet diverse resolu...

David Radu, et al. ∙

research

∙ 09/22/2017

On overfitting and asymptotic bias in batch reinforcement learning with partial observability

This paper stands in the context of reinforcement learning with partial ...

Vincent Francois-Lavet, et al. ∙

research

∙ 12/07/2015

How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies

Using deep neural nets as function approximator for reinforcement learni...

Vincent Francois-Lavet, et al. ∙

research

∙ 09/14/2015

Benchmarking for Bayesian Reinforcement Learning

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maxi...

Michael Castronovo, et al. ∙

research

∙ 06/30/2014

Simple connectome inference from partial correlation statistics in calcium imaging

In this work, we propose a simple yet effective solution to the problem ...

Antonio Sutera, et al. ∙

research

∙ 08/23/2012

Optimized Look-Ahead Tree Policies: A Bridge Between Look-Ahead Tree Policies and Direct Policy Search

Direct policy search (DPS) and look-ahead tree (LT) policies are two wid...

Tobias Jung, et al. ∙

research

∙ 08/23/2012

Monte Carlo Search Algorithm Discovery for One Player Games

Much current research in AI and games is being devoted to Monte Carlo se...

Francis Maes, et al. ∙

research

∙ 07/22/2012

Optimal discovery with probabilistic expert advice: finite time analysis and macroscopic optimality

We consider an original problem that arises from the issue of security a...

Sébastien Bubeck, et al. ∙

research

∙ 07/22/2012

Meta-Learning of Exploration/Exploitation Strategies: The Multi-Armed Bandit Case

The exploration/exploitation (E/E) dilemma arises naturally in many subf...

Francis Maes, et al. ∙

research

∙ 12/19/2011

Scenario trees and policy selection for multistage stochastic programming using machine learning

We propose a hybrid algorithmic strategy for complex stochastic optimiza...

Boris Defourny, et al. ∙