NAIL: A General Interactive Fiction Agent

By Matthew J. Hausknecht, Ricky Loynd, Greg Yang, Adith Swaminathan, Jason Williams. 2019

39 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, LLM Agents & Tool Use, Reinforcement Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In LLM Agents & Tool Use

In Reinforcement Learning

Citations in the corpus

Keep CALM and Explore: Language Models for Action Generation in Text-based Games (2020, methodology): “We demonstrated that CALM can generate high-quality, contextuallyrelevant actions even for games unseen in its training set, and when paired with a DRRN agent, outperforms previous approaches on the Jericho benchmark (Hausknecht et al., 2019a) by as much as 69% in terms of average normalized score.”
Interactive Fiction Games: A Colossal Adventure (2019, background): “NAIL (Hausknecht et al. 2019) is the state-of-the-art agent for general interactive fiction game playing (Atkinson et al. 2018).”
Graph Constrained Reinforcement Learning for Natural Language Action Spaces (2020, methodology): “Importantly, TDQN uses the same set of handicaps as KG-A2C allowing a fair comparison between these two algorithms.”
Multi-Stage Episodic Control for Strategic Exploration in Text Games (2022, unknown): “At every step t , the observation from the Jericho game engine contains a description of the state, which is augmented with location and inventory information (by issuing “look” and “inventory” commands) to form o t (Hausknecht et al., 2019).”
Learning Dynamic Belief Graphs to Generalize on Text-Based Games (2020, background): “[16] show that a state-of-the-art model achieves a mere 2.”
Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020, background): “NAIL (Hausknecht et al., 2019b) is the state-of-theart among these “no-learning” agents, employing a series of reliable heuristics for exploring the game, interacting with objects, and building an internal”
Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents (2021, background): “Thus for future research on text-based games, we advocate for more attention towards alternative setups without RL or handicaps (Hausknecht et al., 2019; Yao et al., 2020; Yu et al., 2020).”
What Would Jiminy Cricket Do? Towards Agents That Behave Morally (2021, background): “• NAIL: The NAIL agent uses hand-crafted heuristics to explore its environment and select actions based on the observations Hausknecht et al. (2019).”
Aligning to Social Norms and Values in Interactive Narratives (2022, background): “NAIL is a heuristic rules-based agent created by Hausknecht et al. (2019) to function as a general text game playing agent.”
Toward Automated Quest Generation in Text-Adventure Games (2019, background): “…Haroush et al., 2018; Cˆot´e et al., 2018; Tao et al., 2018; Ammanabrolu and Riedl, 2019a; Hausknecht et al., 2019a; Am-manabrolu and Riedl, 2019b; Hausknecht et al., 2019b), these works focus on creating agents that can play a given game as opposed to being able to automatically generate…”