# Text-based Adventures of the Golovin AI Agent

## TL;DR

This paper introduces Golovin, an AI agent for text-based adventure games that leverages genre-specific language models and task-specific mechanisms, achieving competitive performance in interactive fiction gameplay.

## Contribution

The paper presents a novel approach combining genre-related corpora and specialized mechanisms for tasks like fighting and navigation in text-based games.

## Key findings

- Agent performs comparably to recent competition winners.
- Use of genre-specific language models improves understanding.
- Mechanisms for key tasks enhance gameplay performance.

## Abstract

The domain of text-based adventure games has been recently established as a new challenge of creating the agent that is both able to understand natural language, and acts intelligently in text-described environments. In this paper, we present our approach to tackle the problem. Our agent, named Golovin, takes advantage of the limited game domain. We use genre-related corpora (including fantasy books and decompiled games) to create language models suitable to this domain. Moreover, we embed mechanisms that allow us to specify, and separately handle, important tasks as fighting opponents, managing inventory, and navigating on the game map. We validated usefulness of these mechanisms, measuring agent's performance on the set of 50 interactive fiction games. Finally, we show that our agent plays on a level comparable to the winner of the last year Text-Based Adventure AI Competition.