Interactive Fiction Games: A Colossal Adventure

Matthew Hausknecht, Prithviraj Ammanabrolu, Marc-Alexandre Côté, Xingdi Yuan
9/11/2019
cs.AIcs.CL

Official code: microsoft/jericho (341 stars, GPL-2.0, last commit 2026-09-09). 1 more implementation below.

Abstract

A hallmark of human intelligence is the ability to understand and communicate with language. Interactive Fiction games are fully text-based simulation environments where a player issues text commands to effect change in the environment and progress through the story. We argue that IF games are an excellent testbed for studying language-based autonomous agents. In particular, IF games combine challenges of combinatorial action spaces, language understanding, and commonsense reasoning. To facilitate rapid development of language-based agents, we introduce Jericho, a learning environment for man-made IF games and conduct a comprehensive study of text-agents across a rich set of games, highlighting directions in which agents can improve.

View on arXivView PDF

Code Implementations(2)

microsoft/jerichoOfficial100%
GPL-2.0

A learning environment for man-made Interactive Fiction games.

34149C, C++Oct 2, 20181 months agoGPL-2.0
interactive-fictionreinforcement-learningtext-based-adventure
microsoft/tdqnOfficial100%
MIT

Template-DQN and DRRN agent implementations

2314PythonOct 28, 20193 years agoMIT

Similar Papers

Cite this paper

@article{hausknecht2019interactive,
  title  = {Interactive Fiction Games: A Colossal Adventure},
  author = {Matthew Hausknecht and Prithviraj Ammanabrolu and Marc-Alexandre Côté and Xingdi Yuan},
  year   = {2019},
  eprint = {1909.05398},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1909.05398}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1909.05398.svg)](https://codeofpaper.com/paper/1909.05398)

Discussion