We propose a novel parameterized skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space that supports efficient learning in long-horizon tasks. We propose to leverage off-policy Meta-RL combined with a trajectory-centric smoothness term to learn a set of parameterized skills. Our agent can use these learned skills to construct a three-level hierarchical framework that models a Temporally-extended Parameterized Action Markov Decision Process. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of difficult long-horizon (obstacle-course and robot manipulation) tasks.
@article{arxiv.2206.03597,
title = {Meta-Learning Parameterized Skills},
author = {Haotian Fu and Shangqun Yu and Saket Tiwari and Michael Littman and George Konidaris},
journal= {arXiv preprint arXiv:2206.03597},
year = {2023}
}