1 code implementation • 18 Jan 2024 • Mehdi Zadem, Sergio Mover, Sao Mai Nguyen
In this paper, we propose a novel three-layer HRL algorithm that introduces, at different levels of the hierarchy, both a spatial and a temporal goal abstraction.
Ranked #1 on Hierarchical Reinforcement Learning on Ant + Maze
no code implementations • 14 Sep 2023 • Mehdi Zadem, Sergio Mover, Sao Mai Nguyen
Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning.
no code implementations • 12 Sep 2023 • Mehdi Zadem, Sergio Mover, Sao Mai Nguyen
Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning.