Learning policies for complex tasks that require multiple different skills is a major challenge
in reinforcement learning (RL). It is also a requirement for its deployment in real-world
scenarios. This paper proposes a novel framework for efficient multi-task reinforcement
learning. Our framework trains agents to employ hierarchical policies that decide when to
use a previously learned policy and when to learn a new skill. This enables agents to
continually acquire new skills during different stages of training. Each learned task …

… the technology disclosed relates generally to reinforcement learning, and more
specifically to learning policies for complex tasks that require multiple different skills, and to
efficient multi-task reinforcement learning through multiple training stages. … the disclosed
novel framework for efficient multi-task reinforcement learning trains software agents to
employ hierarchical policies that decide when to use a previously learned policy and when
to learn a new skill. This enables agents to continually acquire new skills during different …