Search Results for author: Freek Stulp

Found 10 papers, 1 papers with code

Learning to Exploit Elastic Actuators for Quadruped Locomotion

no code implementations15 Sep 2022 Antonin Raffin, Daniel Seidel, Jens Kober, Alin Albu-Schäffer, João Silvério, Freek Stulp

Spring-based actuators in legged locomotion provide energy-efficiency and improved performance, but increase the difficulty of controller design.

Smooth Exploration for Robotic Reinforcement Learning

4 code implementations12 May 2020 Antonin Raffin, Jens Kober, Freek Stulp

We evaluate gSDE both in simulation, on PyBullet continuous control tasks, and directly on three different real robots: a tendon-driven elastic robot, a quadruped and an RC car.

Continuous Control reinforcement-learning +1

Comparing Semi-Parametric Model Learning Algorithms for Dynamic Model Estimation in Robotics

no code implementations27 Jun 2019 Sebastian Riedel, Freek Stulp

Physical modeling of robotic system behavior is the foundation for controlling many robotic mechanisms to a satisfactory degree.

BIG-bench Machine Learning regression

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.

Bayesian Optimization

Policy Search in Continuous Action Domains: an Overview

no code implementations13 Mar 2018 Olivier Sigaud, Freek Stulp

Continuous action policy search is currently the focus of intensive research, driven both by the recent success of deep reinforcement learning algorithms and the emergence of competitors based on evolutionary algorithms.

Bayesian Optimization Evolutionary Algorithms +2

Proximodistal Exploration in Motor Learning as an Emergent Property of Optimization

no code implementations14 Dec 2017 Freek Stulp, Pierre-Yves Oudeyer

Here, we formulate and study computationally the hypothesis that such patterns can emerge spontaneously as the result of a family of stochastic optimization processes (evolution strategies with covariance-matrix adaptation), without an innate encoding of a maturational schedule.

Stochastic Optimization

Gated networks: an inventory

no code implementations10 Dec 2015 Olivier Sigaud, Clément Masson, David Filliat, Freek Stulp

Gated networks are networks that contain gating connections, in which the outputs of at least two neurons are multiplied.

Activity Recognition

Learning and Reasoning with Action-Related Places for Robust Mobile Manipulation

no code implementations18 Jan 2014 Freek Stulp, Andreas Fedrizzi, Lorenz Mösenlechner, Michael Beetz

We propose the concept of Action-Related Place (ARPlace) as a powerful and flexible representation of task-related place in the context of mobile manipulation.

Position

Path Integral Policy Improvement with Covariance Matrix Adaptation

no code implementations18 Jun 2012 Freek Stulp, Olivier Sigaud

There has been a recent focus in reinforcement learning on addressing continuous state and action problems by optimizing parameterized policies.

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