当前位置: X-MOL 学术arXiv.cs.CL › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
arXiv - CS - Computation and Language Pub Date : 2021-06-09 , DOI: arxiv-2106.05387
Keerthiram Murugesan, Subhajit Chaudhury, Kartik Talamadupula

Text-based games (TBGs) have become a popular proving ground for the demonstration of learning-based agents that make decisions in quasi real-world settings. The crux of the problem for a reinforcement learning agent in such TBGs is identifying the objects in the world, and those objects' relations with that world. While the recent use of text-based resources for increasing an agent's knowledge and improving its generalization have shown promise, we posit in this paper that there is much yet to be learned from visual representations of these same worlds. Specifically, we propose to retrieve images that represent specific instances of text observations from the world and train our agents on such images. This improves the agent's overall understanding of the game 'scene' and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship. We show that incorporating such images improves the performance of agents in various TBG settings.

中文翻译:

旁观者之眼:改进基于文本的强化学习代理的关系泛化

基于文本的游戏 (TBG) 已成为演示基于学习的代理的流行试验场,这些代理在准现实世界中做出决策。在这种 TBG 中,强化学习代理的问题的关键是识别世界上的对象,以及这些对象与那个世界的关系。虽然最近使用基于文本的资源来增加代理的知识和提高其泛化能力已显示出前景,但我们在本文中认为,从这些相同世界的视觉表示中还有很多东西需要学习。具体来说,我们建议从世界中检索代表文本观察特定实例的图像,并在这些图像上训练我们的代理。这提高了代理对游戏“场景”和物体与其周围世界关系的整体理解,并且提供的各种视觉表示允许代理生成更好的关系概括。我们表明,合并这些图像可以提高代理在各种 TBG 设置中的性能。
更新日期:2021-06-11
down
wechat
bug