Meta-Learning Parameterized Skills
This addresses the challenge of sample efficiency in complex, long-horizon reinforcement learning tasks, though it appears incremental as it builds on existing Meta-RL and hierarchical frameworks.
The paper tackles the problem of learning transferable parameterized skills for efficient learning in long-horizon tasks, using off-policy Meta-RL with a smoothness term, and demonstrates that the algorithm enables agents to solve difficult obstacle-course and robot manipulation tasks.
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.