论文标题
在您采取行动之前询问：通过提出问题来推广到新颖的环境
Ask Before You Act: Generalising to Novel Environments by Asking Questions
论文作者
论文摘要
解决时间扩展的任务是大多数增强学习（RL）算法的挑战[ARXIV：1906.07343]。我们研究了RL代理商学习提出自然语言问题的能力，以了解其环境并在新颖，时间扩展的环境中实现更大的概括性能。我们通过赋予该代理商的能力来向全知的甲骨文提出“是，不”问题来做到这一点。这使代理商可以获得有关手头任务的指导，同时限制了对新信息的访问。为了在时间扩展的任务的背景下研究这种自然语言问题，我们首先在迷你网格环境中训练我们的代理商。然后，我们将受过训练的代理转移到另一个更艰难的环境中。与无法提出问题的基线代理相比，我们观察到概括性能的显着提高。通过将其对自然语言在环境中的理解，代理可以推理其环境的动态，以至于它在新型环境中部署时可以提出新的，相关的问题。
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 to new information. To study the emergence of such natural language questions in the context of temporally-extended tasks we first train our agent in a Mini-Grid environment. We then transfer the trained agent to a different, harder environment. We observe a significant increase in generalisation performance compared to a baseline agent unable to ask questions. Through grounding its understanding of natural language in its environment, the agent can reason about the dynamics of its environment to the point that it can ask new, relevant questions when deployed in a novel environment.
