NAIL: A General Interactive Fiction Agent
Matthew Hausknecht, Ricky Loynd, Greg Yang, Adith Swaminathan, Jason, D. Williams

TL;DR
NAIL is an autonomous agent designed for parser-based Interactive Fiction games, demonstrating strong generalization and winning the 2018 Text Adventure AI Competition across twenty unseen games.
Contribution
The paper introduces NAIL, a novel general-purpose AI agent for parser-based IF games, with architecture and insights that enable competitive performance on unseen games.
Findings
NAIL won the 2018 Text Adventure AI Competition
NAIL successfully played twenty unseen IF games
The architecture enables generalization to new games
Abstract
Interactive Fiction (IF) games are complex textual decision making problems. This paper introduces NAIL, an autonomous agent for general parser-based IF games. NAIL won the 2018 Text Adventure AI Competition, where it was evaluated on twenty unseen games. This paper describes the architecture, development, and insights underpinning NAIL's performance.
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
TopicsNatural Language Processing Techniques · Topic Modeling · Artificial Intelligence in Games
