TextWorldExpress: Simulating Text Games at One Million Steps Per Second
Peter A. Jansen, Marc-Alexandre C\^ot\'e

TL;DR
TextWorldExpress is a high-performance simulator for text-based games that increases simulation speed by over a thousand times, enabling large-scale experiments in language understanding and reasoning tasks.
Contribution
The paper introduces TextWorldExpress, a novel simulator that dramatically boosts the speed of text game simulation, facilitating billion-step experiments on standard hardware.
Findings
Simulation throughput exceeds one million steps per second.
Enables billion-step-scale experiments in about one day.
Includes implementations of three common text game benchmarks.
Abstract
Text-based games offer a challenging test bed to evaluate virtual agents at language understanding, multi-step problem-solving, and common-sense reasoning. However, speed is a major limitation of current text-based games, capping at 300 steps per second, mainly due to the use of legacy tooling. In this work we present TextWorldExpress, a high-performance simulator that includes implementations of three common text game benchmarks that increases simulation throughput by approximately three orders of magnitude, reaching over one million steps per second on common desktop hardware. This significantly reduces experiment runtime, enabling billion-step-scale experiments in about one day.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Natural Language Processing Techniques · Software Engineering Research
MethodsTest · SPEED: Separable Pyramidal Pooling EncodEr-Decoder for Real-Time Monocular Depth Estimation on Low-Resource Settings
