Search Results for author: Jean-Baptiste Mouret

Found 35 papers, 19 papers with code

Data-efficient learning of object-centric grasp preferences

no code implementations1 Mar 2022 Yoann Fleytoux, Anji Ma, Serena Ivaldi, Jean-Baptiste Mouret

Our pipeline is based on learning a latent space of grasps with a dataset generated with any state-of-the-art grasp generator (e. g., Dex-Net).

First do not fall: learning to exploit the environment with a damaged humanoid robot

1 code implementation1 Mar 2022 Timothée Anne, Eloïse Dalin, Ivan Bergonzani, Serena Ivaldi, Jean-Baptiste Mouret

Humanoid robots could replace humans in hazardous situations but most of such situations are equally dangerous for them, which means that they have a high chance of being damaged and fall.

An Online Data-Driven Emergency-Response Method for Autonomous Agents in Unforeseen Situations

no code implementations17 Dec 2021 Glenn Maguire, Nicholas Ketz, Praveen Pilly, Jean-Baptiste Mouret

We demonstrate the potential of this approach in a simulated 3D car driving scenario, in which the agent devises a response in under 2 seconds to avoid collisions with objects it has not seen during training.

Prescient teleoperation of humanoid robots

no code implementations2 Jul 2021 Luigi Penco, Jean-Baptiste Mouret, Serena Ivaldi

Humanoid robots could be versatile and intuitive human avatars that operate remotely in inaccessible places: the robot could reproduce in the remote location the movements of an operator equipped with a wearable motion capture device while sending visual feedback to the operator.

Evolving the Behavior of Machines: From Micro to Macroevolution

no code implementations21 Dec 2020 Jean-Baptiste Mouret

Evolution gave rise to creatures that are arguably more sophisticated than the greatest human-designed systems.

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

Fast Online Adaptation in Robotics through Meta-Learning Embeddings of Simulated Priors

1 code implementation10 Mar 2020 Rituraj Kaushik, Timothée Anne, Jean-Baptiste Mouret

Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system with only a few data-points.

Meta-Learning Model-based Reinforcement Learning

Discovering Representations for Black-box Optimization

1 code implementation9 Mar 2020 Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret

Our second insight is that this representation can be used to scale quality diversity optimization to higher dimensions -- but only if we carefully mix solutions generated with the learned representation and those generated with traditional variation operators.

Quality Diversity for Multi-task Optimization

2 code implementations9 Mar 2020 Jean-Baptiste Mouret, Glenn Maguire

However, they cannot solve multiple tasks when the fitness needs to be evaluated independently for each task (e. g., optimizing policies to grasp many different objects).

Adaptive Prior Selection for Repertoire-based Online Adaptation in Robotics

1 code implementation16 Jul 2019 Rituraj Kaushik, Pierre Desreumaux, Jean-Baptiste Mouret

Repertoire-based learning is a data-efficient adaptation approach based on a two-step process in which (1) a large and diverse set of policies is learned in simulation, and (2) a planning or learning algorithm chooses the most appropriate policies according to the current situation (e. g., a damaged robot, a new object, etc.).

Meta-Learning online learning

Evolving embodied intelligence from materials to machines

no code implementations17 Jan 2019 David Howard, Agoston E. Eiben, Danielle Frances Kennedy, Jean-Baptiste Mouret, Philip Valencia, Dave Winkler

Natural lifeforms specialise to their environmental niches across many levels; from low-level features such as DNA and proteins, through to higher-level artefacts including eyes, limbs, and overarching body plans.

A survey on policy search algorithms for learning robot controllers in a handful of trials

no code implementations6 Jul 2018 Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Freek Stulp, Sylvain Calinon, Jean-Baptiste Mouret

Most policy search algorithms require thousands of training episodes to find an effective policy, which is often infeasible with a physical robot.

Multi-objective Model-based Policy Search for Data-efficient Learning with Sparse Rewards

1 code implementation25 Jun 2018 Rituraj Kaushik, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties.

Continuous Control Efficient Exploration

Data-Efficient Design Exploration through Surrogate-Assisted Illumination

2 code implementations15 Jun 2018 Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret

Design optimization techniques are often used at the beginning of the design process to explore the space of possible designs.

Data-efficient Neuroevolution with Kernel-Based Surrogate Models

1 code implementation15 Apr 2018 Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret

Surrogate-assistance approaches have long been used in computationally expensive domains to improve the data-efficiency of optimization algorithms.

Discovering the Elite Hypervolume by Leveraging Interspecies Correlation

1 code implementation11 Apr 2018 Vassilis Vassiliades, Jean-Baptiste Mouret

Evolution has produced an astonishing diversity of species, each filling a different niche.

Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics

1 code implementation20 Sep 2017 Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties.

Continuous Control Legged Robots

Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search

1 code implementation20 Sep 2017 Rémi Pautrat, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret

One of the most interesting features of Bayesian optimization for direct policy search is that it can leverage priors (e. g., from simulation or from previous tasks) to accelerate learning on a robot.

Legged Robots Transfer Learning

Black-Box Data-efficient Policy Search for Robotics

2 code implementations21 Mar 2017 Konstantinos Chatzilygeroudis, Roberto Rama, Rituraj Kaushik, Dorian Goepp, Vassilis Vassiliades, Jean-Baptiste Mouret

The most data-efficient algorithms for reinforcement learning (RL) in robotics are based on uncertain dynamical models: after each episode, they first learn a dynamical model of the robot, then they use an optimization algorithm to find a policy that maximizes the expected return given the model and its uncertainties.

Continuous Control

Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination

4 code implementations13 Feb 2017 Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret

The MAP-Elites algorithm produces a set of high-performing solutions that vary according to features defined by the user.

Efficient Exploration

Adaptive and Resilient Soft Tensegrity Robots

no code implementations10 Feb 2017 John Rieffel, Jean-Baptiste Mouret

Living organisms intertwine soft (e. g., muscle) and hard (e. g., bones) materials, giving them an intrinsic flexibility and resiliency often lacking in conventional rigid robots.

Safety-Aware Robot Damage Recovery Using Constrained Bayesian Optimization and Simulated Priors

no code implementations28 Nov 2016 Vaios Papaspyros, Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Jean-Baptiste Mouret

We compare our new "safety-aware IT&E" algorithm to IT&E and a multi-objective version of IT&E in which the safety constraints are dealt as separate objectives.

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.

Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm

4 code implementations18 Oct 2016 Vassilis Vassiliades, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret

The recently introduced Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) is an evolutionary algorithm capable of producing a large archive of diverse, high-performing solutions in a single run.

Reset-free Trial-and-Error Learning for Robot Damage Recovery

1 code implementation13 Oct 2016 Konstantinos Chatzilygeroudis, Vassilis Vassiliades, Jean-Baptiste Mouret

However, the best RL algorithms for robotics require the robot and the environment to be reset to an initial state after each episode, that is, the robot is not learning autonomously.

Legged Robots

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.

Micro-Data Learning: The Other End of the Spectrum

no code implementations4 Oct 2016 Jean-Baptiste Mouret

Many fields are now snowed under with an avalanche of data, which raises considerable challenges for computer scientists.

Alternating Optimisation and Quadrature for Robust Control

no code implementations24 May 2016 Supratik Paul, Konstantinos Chatzilygeroudis, Kamil Ciosek, Jean-Baptiste Mouret, Michael A. Osborne, Shimon Whiteson

ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy.

Bayesian Optimisation reinforcement-learning

The evolutionary origins of hierarchy

no code implementations23 May 2015 Henok Mengistu, Joost Huizinga, Jean-Baptiste Mouret, Jeff Clune

Hierarchical organization -- the recursive composition of sub-modules -- is ubiquitous in biological networks, including neural, metabolic, ecological, and genetic regulatory networks, and in human-made systems, such as large organizations and the Internet.

Illuminating search spaces by mapping elites

4 code implementations20 Apr 2015 Jean-Baptiste Mouret, Jeff Clune

Interestingly, because MAP-Elites explores more of the search space, it also tends to find a better overall solution than state-of-the-art search algorithms.

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.

The evolutionary origins of modularity

no code implementations11 Jul 2012 Jeff Clune, Jean-Baptiste Mouret, Hod Lipson

A central biological question is how natural organisms are so evolvable (capable of quickly adapting to new environments).

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