arXiv Analytics

Sign in

arXiv:1908.04777 [cs.CL]AbstractReferencesReviewsResources

Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Common Sense to Learn Families of Text-Based Adventure Games

Xusen Yin, Jonathan May

Published 2019-08-13Version 1

We consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text video games when adopting simple strategies that correlate with human-like learning behavior. Specifically, we build agents that learn to tackle simple scenarios before more complex ones (curriculum learning), that are equipped with the contextualized semantics of BERT (and we demonstrate that this provides a measure of common sense), and that familiarize themselves in an unfamiliar environment by navigating before acting. We demonstrate faster training convergence and improved task completion rates over reasonable baselines.

Related articles: Most relevant | Search more
arXiv:1904.04365 [cs.CL] (Published 2019-04-08)
AQuA: An Adversarially Authored Question-Answer Dataset for Common Sense
arXiv:1707.09533 [cs.CL] (Published 2017-07-29)
Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
arXiv:1811.00739 [cs.CL] (Published 2018-11-02)
An Empirical Exploration of Curriculum Learning for Neural Machine Translation
Xuan Zhang et al.