# Transfer in Deep Reinforcement Learning using Knowledge Graphs

## TL;DR

This paper investigates how knowledge graphs can be used to transfer domain knowledge in training reinforcement learning agents for text adventure games, leading to faster learning of effective control policies.

## Contribution

It introduces a novel approach for domain knowledge transfer using knowledge graphs in deep reinforcement learning for text-based games, improving learning efficiency.

## Key findings

- Transfer learning with knowledge graphs accelerates policy learning.
- Methods outperform baseline in diverse text adventure games.
- Faster convergence to high-quality policies observed.

## Abstract

Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language. Prior work has demonstrated that using a knowledge graph as a state representation and question-answering to pre-train a deep Q-network facilitates faster control policy transfer. In this paper, we explore the use of knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. Our methods are tested across multiple computer generated and human authored games, varying in domain and complexity, and demonstrate that our transfer learning methods let us learn a higher-quality control policy faster.