# How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents

arXiv: https://arxiv.org/abs/2002.08795 · HTML: https://mlsanity.com/paper/2002.08795/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 10 of 10)

- [Multi-Stage Episodic Control for Strategic Exploration in Text Games](https://mlsanity.com/paper/2201.01251/) (2022)
- [Reading and Acting while Blindfolded: The Need for Semantics in Text Game Agents](https://mlsanity.com/paper/2103.13552/) (2021)
- [Generalization in Text-based Games via Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2109.09968/) (2021)
- [Perceiving the World: Question-guided Reinforcement Learning for Text-based Games](https://mlsanity.com/paper/2204.09597/) (2022)
- [Generative Personas That Behave and Experience Like Humans](https://mlsanity.com/paper/2209.00459/) (2022)
- [Go-Blend behavior and affect](https://mlsanity.com/paper/2109.13388/) (2021)
- [Play with Emotion: Affect-Driven Reinforcement Learning](https://mlsanity.com/paper/2208.12622/) (2022)
- [A Minimal Approach for Natural Language Action Space in Text-based Games](https://mlsanity.com/paper/2305.04082/) (2023)
- [Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environments](https://mlsanity.com/paper/2207.00265/) (2022)
- [A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld](https://mlsanity.com/paper/2302.05244/) (2023)

## Abstract (arXiv)

Text-based games -- in which an agent interacts with the world through textual natural language -- present us with the problem of combinatorially-sized action-spaces. Most current reinforcement learning algorithms are not capable of effectively handling such a large number of possible actions per turn. Poor sample efficiency, consequently, results in agents that are unable to pass bottleneck states, where they are unable to proceed because they do not see the right action sequence to pass the bottleneck enough times to be sufficiently reinforced. Building on prior work using knowledge graphs in reinforcement learning, we introduce two new game state exploration strategies. We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.