Timezone: »

Meta-learning Parameterized Skills
Haotian Fu · Shangqun Yu · Saket Tiwari · Michael L. Littman · George Konidaris

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #718

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 highly difficult long-horizon (obstacle-course and robot manipulation) tasks.

Author Information

Haotian Fu (Brown University)
Shangqun Yu (University of Massachusetts at Amherst)
Saket Tiwari (Brown University)
Michael L. Littman (Brown University)
George Konidaris (Brown)

More from the Same Authors