36 citations · 133 across the 20 of their papers we have counts for
24 papers
Integrating LLMs and Decision Transformers for Language Grounded Generative Quality-Diversity
Achkan Salehi, Stephane Doncieux
Quality-Diversity is a branch of stochastic optimization that is often applied to problems from the Reinforcement Learning and control domains in order to construct repertoires of…
Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control
Achkan Salehi, Stephane Doncieux
Model-based RL/control have gained significant traction in robotics. Yet, these approaches often remain data-inefficient and lack the explainability of hand-engineered solutions. T…
Random Actions vs Random Policies: Bootstrapping Model-Based Direct Policy Search
Elias Hanna, Alex Coninx, Stéphane Doncieux
This paper studies the impact of the initial data gathering method on the subsequent learning of a dynamics model. Dynamics models approximate the true transition function of a giv…
E2R: a Hierarchical-Learning inspired Novelty-Search method to generate diverse repertoires of grasping trajectories
Johann Huber, Oumar Sane, Alex Coninx +2
Robotics grasping refers to the task of making a robotic system pick an object by applying forces and torques on its surface. Despite the recent advances in data-driven approaches,…
Adaptive Asynchronous Control Using Meta-learned Neural Ordinary Differential Equations
Achkan Salehi, Steffen Rühl, Stephane Doncieux
Model-based Reinforcement Learning and Control have demonstrated great potential in various sequential decision making problem domains, including in robotics settings. However, rea…
Automatic Acquisition of a Repertoire of Diverse Grasping Trajectories through Behavior Shaping and Novelty Search
Aurélien Morel, Yakumo Kunimoto, Alex Coninx +1
Grasping a particular object may require a dedicated grasping movement that may also be specific to the robot end-effector. No generic and autonomous method does exist to generate…
Towards QD-suite: developing a set of benchmarks for Quality-Diversity algorithms
Achkan Salehi, Stephane Doncieux
While the field of Quality-Diversity (QD) has grown into a distinct branch of stochastic optimization, a few problems, in particular locomotion and navigation tasks, have become de…
Geodesics, Non-linearities and the Archive of Novelty Search
Achkan Salehi, Alexandre Coninx, Stephane Doncieux
The Novelty Search (NS) algorithm was proposed more than a decade ago. However, the mechanisms behind its empirical success are still not well formalized/understood. This short not…
Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
Giuseppe Paolo, Miranda Coninx, Alban Laflaquière +1
Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions. In these situations, a good strateg…
Exploratory State Representation Learning
Astrid Merckling, Nicolas Perrin-Gilbert, Alex Coninx +1
Not having access to compact and meaningful representations is known to significantly increase the complexity of reinforcement learning (RL). For this reason, it can be useful to p…
Few-shot Quality-Diversity Optimization
Achkan Salehi, Alexandre Coninx, Stephane Doncieux
In the past few years, a considerable amount of research has been dedicated to the exploitation of previous learning experiences and the design of Few-shot and Meta Learning approa…
Selection-Expansion: A Unifying Framework for Motion-Planning and Diversity Search Algorithms
Alexandre Chenu, Nicolas Perrin-Gilbert, Stéphane Doncieux +1
Reinforcement learning agents need a reward signal to learn successful policies. When this signal is sparse or the corresponding gradient is deceptive, such agents need a dedicated…
BR-NS: an Archive-less Approach to Novelty Search
Achkan Salehi, Alexandre Coninx, Stephane Doncieux
As open-ended learning based on divergent search algorithms such as Novelty Search (NS) draws more and more attention from the research community, it is natural to expect that its…
Sparse Reward Exploration via Novelty Search and Emitters
Giuseppe Paolo, Alexandre Coninx, Stephane Doncieux +1
Reward-based optimization algorithms require both exploration, to find rewards, and exploitation, to maximize performance. The need for efficient exploration is even more significa…
Novelty Search makes Evolvability Inevitable
Stephane Doncieux, Giuseppe Paolo, Alban Laflaquière +1
Evolvability is an important feature that impacts the ability of evolutionary processes to find interesting novel solutions and to deal with changing conditions of the problem to s…
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Stephane Doncieux, Nicolas Bredeche, Léni Le Goff +9
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors. Learning algorithm…
State Representation Learning from Demonstration
Astrid Merckling, Alexandre Coninx, Loic Cressot +2
Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, stat…
Unsupervised Learning and Exploration of Reachable Outcome Space
Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx +1
Performing Reinforcement Learning in sparse rewards settings, with very little prior knowledge, is a challenging problem since there is no signal to properly guide the learning pro…
Building an Affordances Map with Interactive Perception
Leni K. Le Goff, Oussama Yaakoubi, Alexandre Coninx +1
Robots need to understand their environment to perform their task. If it is possible to pre-program a visual scene analysis process in closed environments, robots operating in an o…
Bootstrapping Robotic Ecological Perception from a Limited Set of Hypotheses Through Interactive Perception
Léni K. Le Goff, Ghanim Mukhtar, Alexandre Coninx +1
To solve its task, a robot needs to have the ability to interpret its perceptions. In vision, this interpretation is particularly difficult and relies on the understanding of the s…
From exploration to control: learning object manipulation skills through novelty search and local adaptation
Seungsu Kim, Alexandre Coninx, Stephane Doncieux
Programming a robot to deal with open-ended tasks remains a challenge, in particular if the robot has to manipulate objects. Launching, grasping, pushing or any other object intera…
The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Joel Lehman, Jeff Clune, Dusan Misevic +50
Biological evolution provides a creative fount of complex and subtle adaptations, often surprising the scientists who discover them. However, because evolution is an algorithmic pr…
Multi-objective analysis of computational models
Stéphane Doncieux, Jean Liénard, Benoît Girard +2
Computational models are of increasing complexity and their behavior may in particular emerge from the interaction of different parts. Studying such models becomes then more and mo…
Crossing the Reality Gap: a Short Introduction to the Transferability Approach
Jean-Baptiste Mouret, Sylvain Koos, Stéphane Doncieux
In robotics, gradient-free optimization algorithms (e.g. evolutionary algorithms) are often used only in simulation because they require the evaluation of many candidate solutions.…