no code implementations • 12 Nov 2023 • Giovanni Minelli, Vassilis Vassiliades
Quadruped robots have emerged as an evolving technology that currently leverages simulators to develop a robust controller capable of functioning in the real-world without the need for further training.
no code implementations • 5 May 2021 • Giorgos Demosthenous, Vassilis Vassiliades
In addition, we expand the TensorFlow Lite library to include continual learning capabilities, by integrating a simple replay approach into the head of the current transfer learning model.
1 code implementation • 8 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.
no code implementations • 6 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.
1 code implementation • 11 Apr 2018 • Vassilis Vassiliades, Jean-Baptiste Mouret
Evolution has produced an astonishing diversity of species, each filling a different niche.
1 code implementation • 21 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.
no code implementations • 28 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.
5 code implementations • 18 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.
1 code implementation • 13 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.