# Transfer in Deep Reinforcement Learning using Knowledge Graphs

arXiv: https://arxiv.org/abs/1908.06556 · HTML: https://mlsanity.com/paper/1908.06556/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 5 of 5)

- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [Generalization in Text-based Games via Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2109.09968/) (2021)
- [Training a Resilient Q-Network against Observational Interference](https://mlsanity.com/paper/2102.09677/) (2021)
- [ScriptWorld: Text Based Environment For Learning Procedural Knowledge](https://mlsanity.com/paper/2307.03906/) (2023)
- [DiffG-RL: Leveraging Difference between State and Common Sense](https://mlsanity.com/paper/2211.16002/) (2022)

## Abstract (arXiv)

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.