no code implementations • 24 Apr 2024 • Bryan Lim, Manon Flageat, Antoine Cully
We introduce In-context QD, a framework of techniques that aim to elicit the in-context capabilities of pre-trained Large Language Models (LLMs) to generate interesting solutions using the QD archive as context.
1 code implementation • 25 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.
no code implementations • 15 Mar 2024 • Luca Grillotti, Maxence Faldor, Borja G. León, Antoine Cully
A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations.
no code implementations • 6 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.
no code implementations • 12 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.
no code implementations • 10 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.
no code implementations • 3 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.
1 code implementation • 7 Aug 2023 • Felix Chalumeau, Bryan Lim, Raphael Boige, Maxime Allard, Luca Grillotti, Manon Flageat, Valentin Macé, Arthur Flajolet, Thomas Pierrot, Antoine Cully
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax.
no code implementations • 8 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.
1 code implementation • 24 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.
no code implementations • 24 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.
no code implementations • 7 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.
no code implementations • 10 Mar 2023 • Bryan Lim, Manon Flageat, Antoine Cully
However, we also find that not all insights from Deep RL can be effectively translated to QD-RL.
no code implementations • 10 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.
1 code implementation • 7 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.
1 code implementation • 24 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.
1 code implementation • 1 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.
no code implementations • 24 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.
no code implementations • 22 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.
no code implementations • 22 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.
1 code implementation • 9 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.
1 code implementation • 4 Nov 2022 • Manon Flageat, Bryan Lim, Luca Grillotti, Maxime Allard, Simón C. Smith, Antoine Cully
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control.
1 code implementation • 24 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.
no code implementations • 18 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.
no code implementations • 10 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.
1 code implementation • 6 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.
no code implementations • 21 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.
1 code implementation • 12 Apr 2022 • Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Antoine Cully
These adaptation capabilities are directly linked to the behavioural diversity in the repertoire.
no code implementations • 7 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.
1 code implementation • 7 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.
2 code implementations • 2 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.
no code implementations • 16 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.
1 code implementation • 10 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.
no code implementations • 27 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.
no code implementations • 1 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.
no code implementations • 15 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.
1 code implementation • 8 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.
1 code implementation • 17 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).
1 code implementation • 10 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.
1 code implementation • 25 Jun 2020 • Manon Flageat, Antoine Cully
It therefore finds many applications in real-world domain problems such as robotic control.
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.
1 code implementation • 28 May 2019 • Antoine Cully
This approach enables robots to autonomously discover the range of their capabilities while interacting with their environment.
1 code implementation • 5 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.
no code implementations • 19 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.
no code implementations • 9 Mar 2018 • Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Beslon, David M. Bryson, Patryk Chrabaszcz, Nick Cheney, Antoine Cully, Stephane Doncieux, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Frénoy, Christian Gagné, Leni Le Goff, Laura M. Grabowski, Babak Hodjat, Frank Hutter, Laurent Keller, Carole Knibbe, Peter Krcah, Richard E. Lenski, Hod Lipson, Robert MacCurdy, Carlos Maestre, Risto Miikkulainen, Sara Mitri, David E. Moriarty, Jean-Baptiste Mouret, Anh Nguyen, Charles Ofria, Marc Parizeau, David Parsons, Robert T. Pennock, William F. Punch, Thomas S. Ray, Marc Schoenauer, Eric Shulte, Karl Sims, Kenneth O. Stanley, François Taddei, Danesh Tarapore, Simon Thibault, Westley Weimer, Richard Watson, Jason Yosinski
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
2 code implementations • 12 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.
1 code implementation • 12 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.
1 code implementation • 22 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.
no code implementations • 5 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.
2 code implementations • 13 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.