NAIL: A General Interactive Fiction Agent
- Matthew Hausknecht ,
- Ricky Loynd ,
- Greg Yang ,
- Adith Swaminathan ,
- Jason Williams
arXiv: Machine Learning |
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.
Publication Downloads
NAIL Agent
July 2, 2019
NAIL agent provides the source code for an agent which won the 2018 Text-Based Adventure AI Competition. The repository will be also used to release further improvements as we developed better RL approaches to the text games domain.