Eye of the Beholder: Improved Relation Generalization for Text-Based Reinforcement Learning Agents

Authors

  • Keerthiram Murugesan IBM Research
  • Subhajit Chaudhury IBM Research
  • Kartik Talamadupula IBM Research

DOI:

https://doi.org/10.1609/aaai.v36i10.21358

Keywords:

Speech & Natural Language Processing (SNLP), Knowledge Representation And Reasoning (KRR), Computer Vision (CV), Reasoning Under Uncertainty (RU)

Abstract

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.

Downloads

Published

2022-06-28

How to Cite

Murugesan, K., Chaudhury, S., & Talamadupula, K. (2022). Eye of the Beholder: Improved Relation Generalization for Text-Based Reinforcement Learning Agents. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 11094-11102. https://doi.org/10.1609/aaai.v36i10.21358

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing