ScriptWorld: Text Based Environment For Learning Procedural Knowledge

TL;DR

ScriptWorld introduces a novel text-based environment for teaching agents real-world daily chores, leveraging scripts dataset and pre-trained language models to enhance reinforcement learning in realistic scenarios.

Contribution

It is the first interactive text-based environment focused on real-world activities using scripts dataset, and demonstrates the benefit of pre-trained language models in such settings.

Findings

Pre-trained language models improve agent performance.

Environment covers 10 daily activities.

RL agents can learn real-world tasks effectively.

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. We release the environment via Github: https://github.com/Exploration-Lab/ScriptWorld