no code implementations • 22 May 2023 • Dionis Totsila, Konstantinos Chatzilygeroudis, Denis Hadjivelichkov, Valerio Modugno, Ioannis Hatzilygeroudis, Dimitrios Kanoulas
In this work, we bridge the gap between generic neural network policies and dynamical system-based policies, and we introduce Autonomous Neural Dynamic Policies (ANDPs) that: (a) are based on autonomous dynamical systems, (b) always produce asymptotically stable behaviors, and (c) are more flexible than traditional stable dynamical system-based policies.
1 code implementation • 18 Oct 2022 • Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Bryan Lim, Antoine Cully
Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills.
2 code implementations • 12 Apr 2022 • Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Antoine Cully
These adaptation capabilities are directly linked to the behavioural diversity in the repertoire.
1 code implementation • 18 Mar 2022 • Matthias Mayr, Faseeh Ahmad, Konstantinos Chatzilygeroudis, Luigi Nardi, Volker Krueger
We introduce an approach that provides a combination of task-level planning with targeted learning of scenario-specific parameters for skill-based systems.
Bayesian Optimization Multi-Objective Reinforcement Learning
1 code implementation • 27 Sep 2021 • Matthias Mayr, Konstantinos Chatzilygeroudis, Faseeh Ahmad, Luigi Nardi, Volker Krueger
Reinforcement Learning (RL) is a powerful mathematical framework that allows robots to learn complex skills by trial-and-error.
2 code implementations • 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 • 25 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.
1 code implementation • 20 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.
2 code implementations • 20 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.
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.
1 code implementation • 22 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.
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.
no code implementations • 5 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.
no code implementations • 24 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.