TextWorldExpress: Simulating Text Games at One Million Steps Per Second

August 01, 2022 · 🏛 Conference of the European Chapter of the Association for Computational Linguistics

"No code URL or promise found in abstract"
"HuggingFace models found (backfill)"

Evidence collected by the PWNC Scanner

Authors Peter A. Jansen, Marc-Alexandre Côté arXiv ID 2208.01174 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 10 Venue Conference of the European Chapter of the Association for Computational Linguistics Repository https://huggingface.co/spaces/MarcCote/TextWorldExpress Last Checked 7 days ago

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.