Search Results for author: Antoine Cully

Found 49 papers, 25 papers with code

Multi-Objective Quality-Diversity for Crystal Structure Prediction

1 code implementation25 Mar 2024 Hannah Janmohamed, Marta Wolinska, Shikha Surana, Thomas Pierrot, Aron Walsh, Antoine Cully

This approach overlooks other potentially interesting materials that lie in neighbouring local minima and have different material properties such as conductivity or resistance to deformation.

Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms

no code implementations6 Mar 2024 Marta Wolinska, Aron Walsh, Antoine Cully

Consequently, we also show the value of using neural networks to model crystal properties and enable the identification of novel composition--structure combinations.

Beyond Expected Return: Accounting for Policy Reproducibility when Evaluating Reinforcement Learning Algorithms

no code implementations12 Dec 2023 Manon Flageat, Bryan Lim, Antoine Cully

We highlight that existing procedures that only use the expected return are limited on two fronts: first an infinite number of return distributions with a wide range of performance-reproducibility trade-offs can have the same expected return, limiting its effectiveness when used for comparing policies; second, the expected return metric does not leave any room for practitioners to choose the best trade-off value for considered applications.

Bayesian Optimisation Reinforcement Learning (RL)

Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning

no code implementations10 Dec 2023 Maxence Faldor, Félix Chalumeau, Manon Flageat, Antoine Cully

A fundamental trait of intelligence involves finding novel and creative solutions to address a given challenge or to adapt to unforeseen situations.

Continuous Control Evolutionary Algorithms +1

Mix-ME: Quality-Diversity for Multi-Agent Learning

no code implementations3 Nov 2023 Garðar Ingvarsson, Mikayel Samvelyan, Bryan Lim, Manon Flageat, Antoine Cully, Tim Rocktäschel

In many real-world systems, such as adaptive robotics, achieving a single, optimised solution may be insufficient.

Continuous Control

Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces

no code implementations8 Jun 2023 Raphael Boige, Guillaume Richard, Jérémie Dona, Thomas Pierrot, Antoine Cully

While early QD algorithms view the objective and descriptor functions as black-box functions, novel tools have been introduced to use gradient information to accelerate the search and improve overall performance of those algorithms over continuous input spaces.

Drug Discovery Image Generation +1

Benchmark tasks for Quality-Diversity applied to Uncertain domains

1 code implementation24 Apr 2023 Manon Flageat, Luca Grillotti, Antoine Cully

In this paper, we propose a first set of benchmark tasks to analyse and estimate the performance of UQD algorithms.

Quality-Diversity Optimisation on a Physical Robot Through Dynamics-Aware and Reset-Free Learning

no code implementations24 Apr 2023 Simón C. Smith, Bryan Lim, Hannah Janmohamed, Antoine Cully

This method uses a dynamics model, learned from interactions between the robot and the environment, to predict the robot's behaviour and improve sample efficiency.

Don't Bet on Luck Alone: Enhancing Behavioral Reproducibility of Quality-Diversity Solutions in Uncertain Domains

no code implementations7 Apr 2023 Luca Grillotti, Manon Flageat, Bryan Lim, Antoine Cully

Quality-Diversity (QD) algorithms are designed to generate collections of high-performing solutions while maximizing their diversity in a given descriptor space.

Enhancing MAP-Elites with Multiple Parallel Evolution Strategies

no code implementations10 Mar 2023 Manon Flageat, Bryan Lim, Antoine Cully

With the development of fast and massively parallel evaluations in many domains, Quality-Diversity (QD) algorithms, that already proved promising in a large range of applications, have seen their potential multiplied.

MAP-Elites with Descriptor-Conditioned Gradients and Archive Distillation into a Single Policy

1 code implementation7 Mar 2023 Maxence Faldor, Félix Chalumeau, Manon Flageat, Antoine Cully

Quality-Diversity algorithms, such as MAP-Elites, are a branch of Evolutionary Computation generating collections of diverse and high-performing solutions, that have been successfully applied to a variety of domains and particularly in evolutionary robotics.

Improving the Data Efficiency of Multi-Objective Quality-Diversity through Gradient Assistance and Crowding Exploration

1 code implementation24 Feb 2023 Hannah Janmohamed, Thomas Pierrot, Antoine Cully

We show that MOME-PGX is between 4. 3 and 42 times more data-efficient than MOME and doubles the performance of MOME, NSGA-II and SPEA2 in challenging environments.

Evolutionary Algorithms

Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains

1 code implementation1 Feb 2023 Manon Flageat, Antoine Cully

Second, we propose a new methodology to evaluate Uncertain QD approaches, relying on a new per-generation sampling budget and a set of existing and new metrics specifically designed for Uncertain QD.

Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems

no code implementations24 Nov 2022 Felix Chalumeau, Thomas Pierrot, Valentin Macé, Arthur Flajolet, Karim Beguir, Antoine Cully, Nicolas Perrin-Gilbert

Exploration is at the heart of several domains trying to solve control problems such as Reinforcement Learning and QD methods are promising candidates to overcome the challenges associated.

Evolutionary Algorithms

Efficient Exploration using Model-Based Quality-Diversity with Gradients

no code implementations22 Nov 2022 Bryan Lim, Manon Flageat, Antoine Cully

Methods such as Quality-Diversity deals with this by encouraging novel solutions and producing a diversity of behaviours.

Efficient Exploration

Discovering Unsupervised Behaviours from Full-State Trajectories

no code implementations22 Nov 2022 Luca Grillotti, Antoine Cully

We evaluate this approach on a simulated robotic environment, where the robot has to autonomously discover its abilities from its full-state trajectories.

QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems

1 code implementation9 Nov 2022 Ana-Maria Cretu, Florimond Houssiau, Antoine Cully, Yves-Alexandre de Montjoye

We show the attacks found by QS to consistently equate or outperform, sometimes by a large margin, the best attacks from the literature.


Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains

1 code implementation24 Oct 2022 Manon Flageat, Felix Chalumeau, Antoine Cully

Secondly, we show that in addition to outperforming all the considered baselines, the collections of solutions generated by PGA-MAP-Elites are highly reproducible in uncertain environments, approaching the reproducibility of solutions found by Quality-Diversity approaches built specifically for uncertain applications.

Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity

no code implementations18 Oct 2022 Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Bryan Lim, Antoine Cully

Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills.

Efficient Learning of Locomotion Skills through the Discovery of Diverse Environmental Trajectory Generator Priors

no code implementations10 Oct 2022 Shikha Surana, Bryan Lim, Antoine Cully

Data-driven learning based methods have recently been particularly successful at learning robust locomotion controllers for a variety of unstructured terrains.

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

1 code implementation6 Oct 2022 Felix Chalumeau, Raphael Boige, Bryan Lim, Valentin Macé, Maxime Allard, Arthur Flajolet, Antoine Cully, Thomas Pierrot

Recent work has shown that training a mixture of policies, as opposed to a single one, that are driven to explore different regions of the state-action space can address this shortcoming by generating a diverse set of behaviors, referred to as skills, that can be collectively used to great effect in adaptation tasks or for hierarchical planning.

reinforcement-learning Reinforcement Learning (RL)

Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms

no code implementations21 Apr 2022 Luca Grillotti, Antoine Cully

Quality-Diversity algorithms provide efficient mechanisms to generate large collections of diverse and high-performing solutions, which have shown to be instrumental for solving downstream tasks.

Hierarchical Quality-Diversity for Online Damage Recovery

1 code implementation12 Apr 2022 Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Antoine Cully

These adaptation capabilities are directly linked to the behavioural diversity in the repertoire.

Learning to Walk Autonomously via Reset-Free Quality-Diversity

no code implementations7 Apr 2022 Bryan Lim, Alexander Reichenbach, Antoine Cully

Quality-Diversity (QD) algorithms can discover large and complex behavioural repertoires consisting of both diverse and high-performing skills.

Multi-Objective Quality Diversity Optimization

1 code implementation7 Feb 2022 Thomas Pierrot, Guillaume Richard, Karim Beguir, Antoine Cully

In this work, we consider the problem of Quality-Diversity (QD) optimization with multiple objectives.

Accelerated Quality-Diversity through Massive Parallelism

2 code implementations2 Feb 2022 Bryan Lim, Maxime Allard, Luca Grillotti, Antoine Cully

With recent advances in simulators that run on accelerators, thousands of evaluations can now be performed in parallel on single GPU/TPU.

Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoires

no code implementations16 Sep 2021 Bryan Lim, Luca Grillotti, Lorenzo Bernasconi, Antoine Cully

In this paper, we propose Dynamics-Aware Quality-Diversity (DA-QD), a framework to improve the sample efficiency of QD algorithms through the use of dynamics models.

Zero-Shot Learning

Unsupervised Behaviour Discovery with Quality-Diversity Optimisation

1 code implementation10 Jun 2021 Luca Grillotti, Antoine Cully

In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot.

Dimensionality Reduction Evolutionary Algorithms

Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution

no code implementations27 Apr 2021 Nemanja Rakicevic, Antoine Cully, Petar Kormushev

This paper proposes a novel method for diversity-based policy search via Neuroevolution, that leverages learned representations of the policy network parameters, by performing policy search in this learned representation space.

Continuous Control

On the Importance of Distraction-Robust Representations for Robot Learning

no code implementations1 Jan 2021 Andy Wang, Antoine Cully

Our experimental evaluations demonstrate that representations learned with a traditional dimensionality reduction algorithm are strongly susceptible to distractions in a robot's environment.

Dimensionality Reduction Representation Learning

Policy Manifold Search for Improving Diversity-based Neuroevolution

no code implementations15 Dec 2020 Nemanja Rakicevic, Antoine Cully, Petar Kormushev

Our approach iteratively collects policies according to the QD framework, in order to (i) build a collection of diverse policies, (ii) use it to learn a latent representation of the policy parameters, (iii) perform policy search in the learned latent space.

Continuous Control

Quality-Diversity Optimization: a novel branch of stochastic optimization

1 code implementation8 Dec 2020 Konstantinos Chatzilygeroudis, Antoine Cully, Vassilis Vassiliades, Jean-Baptiste Mouret

In this chapter, we provide a gentle introduction to Quality-Diversity optimization, discuss the main representative algorithms, and the main current topics under consideration in the community.

Stochastic Optimization

Competitiveness of MAP-Elites against Proximal Policy Optimization on locomotion tasks in deterministic simulations

1 code implementation17 Sep 2020 Szymon Brych, Antoine Cully

The increasing importance of robots and automation creates a demand for learnable controllers which can be obtained through various approaches such as Evolutionary Algorithms (EAs) or Reinforcement Learning (RL).

Evolutionary Algorithms Reinforcement Learning (RL)

Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters

1 code implementation10 Jul 2020 Antoine Cully

Our comparisons against CMA-ME and MAP-Elites show that ME-MAP-Elites is faster at providing collections of solutions that are significantly more diverse and higher performing.

Fast and stable MAP-Elites in noisy domains using deep grids

1 code implementation25 Jun 2020 Manon Flageat, Antoine Cully

It therefore finds many applications in real-world domain problems such as robotic control.

Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization

1 code implementation NeurIPS 2021 Thomas Pierrot, Valentin Macé, Félix Chalumeau, Arthur Flajolet, Geoffrey Cideron, Karim Beguir, Antoine Cully, Olivier Sigaud, Nicolas Perrin-Gilbert

This paper proposes a novel algorithm, QDPG, which combines the strength of Policy Gradient algorithms and Quality Diversity approaches to produce a collection of diverse and high-performing neural policies in continuous control environments.

Continuous Control Evolutionary Algorithms

Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors

1 code implementation28 May 2019 Antoine Cully

This approach enables robots to autonomously discover the range of their capabilities while interacting with their environment.

Dimensionality Reduction

AlphaStar: An Evolutionary Computation Perspective

1 code implementation5 Feb 2019 Kai Arulkumaran, Antoine Cully, Julian Togelius

In January 2019, DeepMind revealed AlphaStar to the world-the first artificial intelligence (AI) system to beat a professional player at the game of StarCraft II-representing a milestone in the progress of AI.

Reinforcement Learning (RL) Starcraft II

Hierarchical Behavioral Repertoires with Unsupervised Descriptors

no code implementations19 Apr 2018 Antoine Cully, Yiannis Demiris

This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors.

Quality and Diversity Optimization: A Unifying Modular Framework

2 code implementations12 May 2017 Antoine Cully, Yiannis Demiris

Secondly, we propose algorithms with a new selection mechanism for Quality-Diversity algorithms that outperforms all the algorithms tested in this paper.


MAGAN: Margin Adaptation for Generative Adversarial Networks

1 code implementation12 Apr 2017 Ruohan Wang, Antoine Cully, Hyung Jin Chang, Yiannis Demiris

We propose the Margin Adaptation for Generative Adversarial Networks (MAGANs) algorithm, a novel training procedure for GANs to improve stability and performance by using an adaptive hinge loss function.

Image Generation

Limbo: A Fast and Flexible Library for Bayesian Optimization

1 code implementation22 Nov 2016 Antoine Cully, Konstantinos Chatzilygeroudis, Federico Allocati, Jean-Baptiste Mouret

Limbo is an open-source C++11 library for Bayesian optimization which is designed to be both highly flexible and very fast.

Bayesian Optimization

Towards semi-episodic learning for robot damage recovery

no code implementations5 Oct 2016 Konstantinos Chatzilygeroudis, Antoine Cully, Jean-Baptiste Mouret

The recently introduced Intelligent Trial and Error algorithm (IT\&E) enables robots to creatively adapt to damage in a matter of minutes by combining an off-line evolutionary algorithm and an on-line learning algorithm based on Bayesian Optimization.

Bayesian Optimization

Robots that can adapt like animals

2 code implementations13 Jul 2014 Antoine Cully, Jeff Clune, Danesh Tarapore, Jean-Baptiste Mouret

As robots leave the controlled environments of factories to autonomously function in more complex, natural environments, they will have to respond to the inevitable fact that they will become damaged.

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