English
Related papers

Related papers: Quality-Diversity Optimisation on a Physical Robot…

200 papers

A key aspect of intelligence is the ability to demonstrate a broad spectrum of behaviors for adapting to unexpected situations. Over the past decade, advancements in deep reinforcement learning have led to groundbreaking achievements to…

Machine Learning · Computer Science 2024-06-04 Luca Grillotti , Maxence Faldor , Borja G. León , Antoine Cully

Mixed-precision quantization mostly predetermines the model bit-width settings before actual training due to the non-differential bit-width sampling process, obtaining sub-optimal performance. Worse still, the conventional static…

Artificial Intelligence · Computer Science 2023-02-10 Yingchun Wang , Jingcai Guo , Song Guo , Weizhan Zhang

Mobile soft robots offer compelling applications in fields ranging from urban search and rescue to planetary exploration. A critical challenge of soft robotic control is that the nonlinear dynamics imposed by soft materials often result in…

Robotics · Computer Science 2020-11-26 Kyle Doney , Aikaterini Petridou , Jacob Karaul , Ali Khan , Geoffrey Liu , John Rieffel

Quality-Diversity (QD) algorithms have shown remarkable success in discovering diverse, high-performing solutions, but rely heavily on hand-crafted behavioral descriptors that constrain exploration to predefined notions of diversity.…

Machine Learning · Computer Science 2026-03-05 Saeed Hedayatian , Stefanos Nikolaidis

Soft robotics aims to develop robots able to adapt their behavior across a wide range of unstructured and unknown environments. A critical challenge of soft robotic control is that nonlinear dynamics often result in complex behaviors hard…

Neural and Evolutionary Computing · Computer Science 2023-11-03 John Daly , Daniel Casper , Muhammad Farooq , Andrew James , Ali Khan , Phoenix Mulgrew , Daniel Tyebkhan , Bao Vo , John Rieffel

Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in…

Machine Learning · Computer Science 2019-05-16 Narendra Patwardhan , Zequn Wang

Quality-Diversity optimisation algorithms enable the evolution of collections of both high-performing and diverse solutions. These collections offer the possibility to quickly adapt and switch from one solution to another in case it is not…

Neural and Evolutionary Computing · Computer Science 2023-04-26 Manon Flageat , Antoine Cully

When using Quality Diversity (QD) optimization to solve hard exploration or deceptive search problems, we assume that diversity is extrinsically valuable. This means that diversity is important to help us reach an objective, but is not an…

Neural and Evolutionary Computing · Computer Science 2023-05-16 Ryan Boldi , Lee Spector

Adaptation capabilities, like damage recovery, are crucial for the deployment of robots in complex environments. Several works have demonstrated that using repertoires of pre-trained skills can enable robots to adapt to unforeseen…

Robotics · Computer Science 2022-04-13 Maxime Allard , Simón C. Smith , Konstantinos Chatzilygeroudis , Antoine Cully

Quality diversity (QD) is a growing branch of stochastic optimization research that studies the problem of generating an archive of solutions that maximize a given objective function but are also diverse with respect to a set of specified…

Artificial Intelligence · Computer Science 2021-10-28 Matthew C. Fontaine , Stefanos Nikolaidis

Quality-Diversity algorithms are powerful tools for discovering diverse, high-performing solutions. Recently, Multi-Objective Quality-Diversity (MOQD) extends QD to problems with several objectives while preserving solution diversity. MOQD…

Machine Learning · Computer Science 2025-04-08 Hannah Janmohamed , Antoine Cully

Quality-Diversity (QD) is a concept from Neuroevolution with some intriguing applications to Reinforcement Learning. It facilitates learning a population of agents where each member is optimized to simultaneously accumulate high…

Machine Learning · Computer Science 2020-11-06 Tanmay Gangwani , Jian Peng , Yuan Zhou

Quality-Diversity is a family of evolutionary algorithms that generate diverse, high-performing solutions through local competition principles inspired by natural evolution. While research has focused on improving specific aspects of…

Neural and Evolutionary Computing · Computer Science 2025-02-04 Ryan Bahlous-Boldi , Maxence Faldor , Luca Grillotti , Hannah Janmohamed , Lisa Coiffard , Lee Spector , Antoine Cully

Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the…

Machine Learning · Computer Science 2018-03-20 Tuomas Haarnoja , Vitchyr Pong , Aurick Zhou , Murtaza Dalal , Pieter Abbeel , Sergey Levine

Recent advances in AI have led to significant results in robotic learning, including natural language-conditioned planning and efficient optimization of controllers using generative models. However, the interaction data remains the…

Traditional optimization algorithms search for a single global optimum that maximizes (or minimizes) the objective function. Multimodal optimization algorithms search for the highest peaks in the search space that can be more than one.…

Neural and Evolutionary Computing · Computer Science 2020-12-18 Konstantinos Chatzilygeroudis , Antoine Cully , Vassilis Vassiliades , Jean-Baptiste Mouret

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were…

Neural and Evolutionary Computing · Computer Science 2023-09-11 Felix Chalumeau , Raphael Boige , Bryan Lim , Valentin Macé , Maxime Allard , Arthur Flajolet , Antoine Cully , Thomas Pierrot

Autonomous skill discovery aims to enable robots to acquire diverse behaviors without explicit supervision. Learning such behaviors directly on physical hardware remains challenging due to safety and data efficiency constraints. Existing…

Robotics · Computer Science 2025-08-29 Luca Grillotti , Lisa Coiffard , Oscar Pang , Maxence Faldor , Antoine Cully

Quality-Diversity optimisation (QD) has proven to yield promising results across a broad set of applications. However, QD approaches struggle in the presence of uncertainty in the environment, as it impacts their ability to quantify the…

Neural and Evolutionary Computing · Computer Science 2023-03-28 Manon Flageat , Antoine Cully

While legged robots have achieved significant advancements in recent years, ensuring the robustness of their controllers on unstructured terrains remains challenging. It requires generating diverse and challenging unstructured terrains to…

Robotics · Computer Science 2025-10-13 Arthur Esquerre-Pourtère , Minsoo Kim , Jaeheung Park