Language grounded task-adaptation in reinforcement learning

Over its lifetime, a Reinforcement Learning agent is often instructed to perform dierent tasks. How to eciently adapt a previously learned control policy from one task to another, remains an open research question. In this paper, we investigate how instructions formulated in natural language can enable faster and more eective task adaptation. Our proposed method is capable of assessing, given a set of developed base control policies, which base policy will be the most qualied to adapt to a new unseen task.

ISBN:978-2-87587-074-2

Publication year:2020

Accessibility:Closed