no code implementations • 15 Nov 2022 • Matthias Hutsebaut-Buysse, Kevin Mets, Tom De Schepper, Steven Latré
Finding an object of a specific class in an unseen environment remains an unsolved navigation problem.
1 code implementation • ICML Workshop LaReL 2020 • Matthias Hutsebaut-Buysse, Kevin Mets, Steven Latré
Reinforcement learning (RL) algorithms typically start tabula rasa, without any prior knowledge of the environment, and without any prior skills.
no code implementations • 9 Oct 2019 • Matthias Hutsebaut-Buysse, Kevin Mets, Steven Latré
Over its lifetime, a reinforcement learning agent is often tasked with different tasks.