Search Results for author:
Found 50 papers, 25 papers with code
Large Language Models as In-context AI Generators for Quality-Diversity
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.
Multi-Objective Quality-Diversity for Crystal Structure Prediction
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.
Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics
A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations.
Illuminating the property space in crystal structure prediction using Quality-Diversity algorithms
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
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.
Synergizing Quality-Diversity with Descriptor-Conditioned Reinforcement Learning
A fundamental trait of intelligence involves finding novel and creative solutions to address a given challenge or to adapt to unforeseen situations.
Mix-ME: Quality-Diversity for Multi-Agent Learning
In many real-world systems, such as adaptive robotics, achieving a single, optimised solution may be insufficient.
QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax.
Gradient-Informed Quality Diversity for the Illumination of Discrete Spaces
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.
Benchmark tasks for Quality-Diversity applied to Uncertain domains
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
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
Quality-Diversity (QD) algorithms are designed to generate collections of high-performing solutions while maximizing their diversity in a given descriptor space.
Understanding the Synergies between Quality-Diversity and Deep Reinforcement Learning
However, we also find that not all insights from Deep RL can be effectively translated to QD-RL.
Enhancing MAP-Elites with Multiple Parallel Evolution Strategies
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
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
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.
Uncertain Quality-Diversity: Evaluation methodology and new methods for Quality-Diversity in Uncertain Domains
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
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.
Discovering Unsupervised Behaviours from Full-State Trajectories
We evaluate this approach on a simulated robotic environment, where the robot has to autonomously discover its abilities from its full-state trajectories.
Efficient Exploration using Model-Based Quality-Diversity with Gradients
Methods such as Quality-Diversity deals with this by encouraging novel solutions and producing a diversity of behaviours.
QuerySnout: Automating the Discovery of Attribute Inference Attacks against Query-Based Systems
We show the attacks found by QS to consistently equate or outperform, sometimes by a large margin, the best attacks from the literature.
Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control.
Empirical analysis of PGA-MAP-Elites for Neuroevolution in Uncertain Domains
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
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
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
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.
Relevance-guided Unsupervised Discovery of Abilities with Quality-Diversity Algorithms
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
These adaptation capabilities are directly linked to the behavioural diversity in the repertoire.
Learning to Walk Autonomously via Reset-Free Quality-Diversity
Quality-Diversity (QD) algorithms can discover large and complex behavioural repertoires consisting of both diverse and high-performing skills.
Multi-Objective Quality Diversity Optimization
In this work, we consider the problem of Quality-Diversity (QD) optimization with multiple objectives.
Accelerated Quality-Diversity through Massive Parallelism
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
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.
Unsupervised Behaviour Discovery with Quality-Diversity Optimisation
In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot.
Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution
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.
On the Importance of Distraction-Robust Representations for Robot Learning
Our experimental evaluations demonstrate that representations learned with a traditional dimensionality reduction algorithm are strongly susceptible to distractions in a robot's environment.
Policy Manifold Search for Improving Diversity-based Neuroevolution
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.
Quality-Diversity Optimization: a novel branch of stochastic optimization
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.
Competitiveness of MAP-Elites against Proximal Policy Optimization on locomotion tasks in deterministic simulations
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).
Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters
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
It therefore finds many applications in real-world domain problems such as robotic control.
Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
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.
Autonomous skill discovery with Quality-Diversity and Unsupervised Descriptors
This approach enables robots to autonomously discover the range of their capabilities while interacting with their environment.
AlphaStar: An Evolutionary Computation Perspective
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.
Hierarchical Behavioral Repertoires with Unsupervised Descriptors
This paper presents a step in this direction with hierarchical behavioral repertoires that stack several behavioral repertoires to generate sophisticated behaviors.
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them.
Quality and Diversity Optimization: A Unifying Modular Framework
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
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.
Limbo: A Fast and Flexible Library for Bayesian Optimization
Limbo is an open-source C++11 library for Bayesian optimization which is designed to be both highly flexible and very fast.
Towards semi-episodic learning for robot damage recovery
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.
Robots that can adapt like animals
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.
