ScriptWorld: Text Based Environment for Learning Procedural Knowledge
Lists
Only you see this
Abstract
Text-based games provide a framework for developing natural language understanding and commonsense knowledge about the world in reinforcement learning based agents. Existing text-based environments often rely on fictional situations and characters to create a gaming framework and are far from real-world scenarios. In this paper, we introduce ScriptWorld: a text-based environment for teaching agents about real-world daily chores and hence imparting commonsense knowledge. To the best of our knowledge, it is the first interactive text-based gaming framework that consists of daily real-world human activities designed using scripts dataset. We provide gaming environments for 10 daily activities and perform a detailed analysis of the proposed environment. We develop RL-based baseline models/agents to play the games in ScriptWorld. To understand the role of language models in such environments, we leverage features obtained from pre-trained language models in the RL agents. Our experiments show that prior knowledge obtained from a pre-trained language model helps to solve real-world text-based gaming environments.
BibTeX
@inproceedings{joshi2023scriptworld,
author = {Abhinav Joshi and Areeb Ahmad and Umang Pandey and Ashutosh Modi},
title = {{ScriptWorld: Text Based Environment for Learning Procedural Knowledge}},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2023},
doi = {10.24963/ijcai.2023/566},
}