Ask Before You Act: Generalising to Novel Environments by Asking Questions. (arXiv:2209.04665v2 [cs.AI] UPDATED)

Solving temporally-extended tasks is a challenge for most reinforcement
learning (RL) algorithms [arXiv:1906.07343]. We investigate the ability of an
RL agent to learn to ask natural language questions as a tool to understand its
environment and achieve greater generalisation performance in novel,
temporally-extended environments. We do this by endowing this agent with the
ability of asking "yes-no" questions to an all-knowing Oracle. This allows the
agent to obtain guidance regarding the task at hand, while limiting the access …

arxiv environments