Fast Task-Adaptation for Tasks Labeled Using Natural Language in Reinforcement Learning
This addresses the challenge of task adaptation in reinforcement learning for lifelong learning agents, though it appears incremental as it builds on existing policy adaptation methods.
The paper tackles the problem of efficiently adapting reinforcement learning policies between tasks by using natural language instructions, resulting in a method that selects the best base policy for adaptation to new tasks.
Over its lifetime, a reinforcement learning agent is often tasked with different tasks. How to efficiently 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 effective task adaptation. This can serve as the basis for developing language instructed skills, which can be used in a lifelong learning setting. Our method is capable of assessing, given a set of developed base control policies, which policy will adapt best to a new unseen task.