NAIL: A General Interactive Fiction Agent
arXiv:1902.04259
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.
References in corpus (6)
- Efficient Estimation of Word Representations in Vector Space
- Skip-Thought Vectors
- Language Understanding for Text-based Games Using Deep Reinforcement Learning
- Counting to Explore and Generalize in Text-based Games
- Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
- Using reinforcement learning to learn how to play text-based games
Cited by in corpus (10)
- Learning Dynamic Belief Graphs to Generalize on Text-Based Games
- Graph Constrained Reinforcement Learning for Natural Language Action Spaces
- Interactive Fiction Games: A Colossal Adventure
- Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
- Interactive Language Learning by Question Answering
- Toward Automated Quest Generation in Text-Adventure Games
- Keep CALM and Explore: Language Models for Action Generation in Text-based Games
- Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents
- Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning
- Generalization in Text-based Games via Hierarchical Reinforcement Learning