no code implementations • 1 Nov 2023 • Olivier Sigaud, Gianluca Baldassarre, Cedric Colas, Stephane Doncieux, Richard Duro, Nicolas Perrin-Gilbert, Vieri Giuliano Santucci
A lot of recent machine learning research papers have ``open-ended learning'' in their title.
1 code implementation • 25 Aug 2023 • 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 well-performing policies/skills that exhibit diversity with respect to a behavior space.
no code implementations • 2 Mar 2023 • Achkan Salehi, Stephane Doncieux
Model-based RL/control have gained significant traction in robotics.
no code implementations • 14 Oct 2022 • Johann Huber, Oumar Sane, Alex Coninx, Faiz Ben Amar, Stephane Doncieux
Robotics grasping refers to the task of making a robotic system pick an object by applying forces and torques on its surface.
no code implementations • 25 Jul 2022 • 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.
no code implementations • 6 May 2022 • Achkan Salehi, Alexandre Coninx, Stephane Doncieux
An argument that is often encountered in the literature is that the archive prevents exploration from backtracking or cycling, i. e. from revisiting previously encountered areas in the behavior space.
no code implementations • 6 May 2022 • Achkan Salehi, Stephane Doncieux
Inspired by recent works on Reinforcement Learning benchmarks, we argue that the identification of challenges faced by QD methods and the development of targeted, challenging, scalable but affordable benchmarks is an important step.
1 code implementation • 2 Nov 2021 • Giuseppe Paolo, Miranda Coninx, Alban Laflaquière, Stephane Doncieux
Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions.
1 code implementation • 14 Sep 2021 • Achkan Salehi, Alexandre Coninx, Stephane Doncieux
Experiments carried in both sparse and dense reward settings using robotic manipulation and navigation benchmarks show that it considerably reduces the number of generations that are required for QD optimization in these environments.
1 code implementation • 8 Apr 2021 • Achkan Salehi, Alexandre Coninx, Stephane Doncieux
In this paper, we discuss an alternative approach to novelty estimation, dubbed Behavior Recognition based Novelty Search (BR-NS), which does not require an archive, makes no assumption on the metrics that can be defined in the behavior space and does not rely on nearest neighbours search.
1 code implementation • 5 Feb 2021 • Giuseppe Paolo, Alexandre Coninx, Stephane Doncieux, Alban Laflaquière
Contrary to existing emitters-based approaches, SERENE separates the search space exploration and reward exploitation into two alternating processes.
no code implementations • 13 May 2020 • Stephane Doncieux, Nicolas Bredeche, Léni Le Goff, Benoît Girard, Alexandre Coninx, Olivier Sigaud, Mehdi Khamassi, Natalia Díaz-Rodríguez, David Filliat, Timothy Hospedales, A. Eiben, Richard Duro
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.
2 code implementations • 13 May 2020 • Stephane Doncieux, Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx
Evolvability is thus a natural byproduct of the search in this context.
1 code implementation • 12 Sep 2019 • Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx, Stephane Doncieux
Results show that TAXONS can find a diverse set of controllers, covering a good part of the ground-truth outcome space, while having no information about such space.
no code implementations • 11 Mar 2019 • Leni K. Le Goff, Oussama Yaakoubi, Alexandre Coninx, Stephane Doncieux
Robots need to understand their environment to perform their task.
no code implementations • 3 Jan 2019 • Seungsu Kim, Alexandre Coninx, Stephane Doncieux
The approach has been validated on two different experiments on the Baxter robot: a ball launching and a joystick manipulation tasks.
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.