1 code implementation • 3 Apr 2024 • Marko Zaric, Jakob Hollenstein, Justus Piater, Erwan Renaudo
Learning actions that are relevant to decision-making and can be executed effectively is a key problem in autonomous robotics.
no code implementations • 8 Jun 2022 • Jakob Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Many Deep Reinforcement Learning (D-RL) algorithms rely on simple forms of exploration such as the additive action noise often used in continuous control domains.
no code implementations • 29 Oct 2020 • Jakob J. Hollenstein, Sayantan Auddy, Matteo Saveriano, Erwan Renaudo, Justus Piater
Sufficient exploration is paramount for the success of a reinforcement learning agent.
no code implementations • 24 Oct 2020 • Jakob J. Hollenstein, Erwan Renaudo, Matteo Saveriano, Justus Piater
Local policy search is performed by most Deep Reinforcement Learning (D-RL) methods, which increases the risk of getting trapped in a local minimum.
Model-based Reinforcement Learning reinforcement-learning +1
no code implementations • 30 Apr 2020 • Rémi Dromnelle, Erwan Renaudo, Guillaume Pourcel, Raja Chatila, Benoît Girard, Mehdi Khamassi
We present a novel arbitration mechanism between learning systems that explicitly measures performance and cost.
no code implementations • 25 Sep 2019 • Jakob J. Hollenstein, Erwan Renaudo, Justus Piater
Most Deep Reinforcement Learning methods perform local search and therefore are prone to get stuck on non-optimal solutions.
Model-based Reinforcement Learning reinforcement-learning +1