158 citations · 680 across the 25 of their papers we have counts for
19 papers · 1 filter
Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind
Clémence Grislain, Hugo Caselles-Dupré, Olivier Sigaud +1
Good teachers always tailor their explanations to the learners. Cognitive scientists model this process under the rationality principle: teachers try to maximise the learner's util…
Making Reinforcement Learning Work on Swimmer
Maël Franceschetti, Coline Lacoux, Ryan Ohouens +2
The SWIMMER environment is a standard benchmark in reinforcement learning (RL). In particular, it is often used in papers comparing or combining RL methods with direct policy searc…
Combining Evolution and Deep Reinforcement Learning for Policy Search: a Survey
Olivier Sigaud
Deep neuroevolution and deep Reinforcement Learning have received a lot of attention in the last years. Some works have compared them, highlighting theirs pros and cons, but an eme…
Offline Reinforcement Learning Hands-On
Louis Monier, Jakub Kmec, Alexandre Laterre +4
Offline Reinforcement Learning (RL) aims to turn large datasets into powerful decision-making engines without any online interactions with the environment. This great promise has m…
Investigating Generalisation in Continuous Deep Reinforcement Learning
Chenyang Zhao, Olivier Sigaud, Freek Stulp +1
Deep Reinforcement Learning has shown great success in a variety of control tasks. However, it is unclear how close we are to the vision of putting Deep RL into practice to solve r…
Interactively shaping robot behaviour with unlabeled human instructions
Anis Najar, Olivier Sigaud, Mohamed Chetouani
In this paper, we propose a framework that enables a human teacher to shape a robot behaviour by interactively providing it with unlabeled instructions. We ground the meaning of in…
CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environments
Pierre Fournier, Olivier Sigaud, Cédric Colas +1
In this paper we study a new reinforcement learning setting where the environment is non-rewarding, contains several possibly related objects of various controllability, and where…
First-order and second-order variants of the gradient descent in a unified framework
Thomas Pierrot, Nicolas Perrin, Olivier Sigaud
In this paper, we provide an overview of first-order and second-order variants of the gradient descent method that are commonly used in machine learning. We propose a general frame…
CEM-RL: Combining evolutionary and gradient-based methods for policy search
Aloïs Pourchot, Olivier Sigaud
Deep neuroevolution and deep reinforcement learning (deep RL) algorithms are two popular approaches to policy search. The former is widely applicable and rather stable, but suffers…
Importance mixing: Improving sample reuse in evolutionary policy search methods
Aloïs Pourchot, Nicolas Perrin, Olivier Sigaud
Deep neuroevolution, that is evolutionary policy search methods based on deep neural networks, have recently emerged as a competitor to deep reinforcement learning algorithms due t…
How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments
Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer
Consistently checking the statistical significance of experimental results is one of the mandatory methodological steps to address the so-called "reproducibility crisis" in deep re…
Accuracy-based Curriculum Learning in Deep Reinforcement Learning
Pierre Fournier, Olivier Sigaud, Mohamed Chetouani +1
In this paper, we investigate a new form of automated curriculum learning based on adaptive selection of accuracy requirements, called accuracy-based curriculum learning. Using a r…
Policy Search in Continuous Action Domains: an Overview
Olivier Sigaud, Freek Stulp
Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of compe…
Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration
Alexandre Péré, Sébastien Forestier, Olivier Sigaud +1
Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments. These explorati…
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms
Cédric Colas, Olivier Sigaud, Pierre-Yves Oudeyer
In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Convers…
Actor-critic versus direct policy search: a comparison based on sample complexity
Arnaud de Froissard de Broissia, Olivier Sigaud
Sample efficiency is a critical property when optimizing policy parameters for the controller of a robot. In this paper, we evaluate two state-of-the-art policy optimization algori…
Gated networks: an inventory
Olivier Sigaud, Clément Masson, David Filliat +1
Gated networks are networks that contain gating connections, in which the outputs of at least two neurons are multiplied. Initially, gated networks were used to learn relationships…
Chi-square Tests Driven Method for Learning the Structure of Factored MDPs
Thomas Degris, Olivier Sigaud, Pierre-Henri Wuillemin
SDYNA is a general framework designed to address large stochastic reinforcement learning problems. Unlike previous model based methods in FMDPs, it incrementally learns the structu…
Path Integral Policy Improvement with Covariance Matrix Adaptation
Freek Stulp, Olivier Sigaud
There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies. PI2 is a recent example of this app…