Abstract
Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the game state as a knowledge graph which is learned during exploration. This graph is used to prune the action space, enabling more efficient exploration. The question of which action to take can be reduced to a question-answering task, a form of transfer learning that pre-trains certain parts of our architecture. In experiments using the TextWorld framework, we show that our proposed technique can learn a control policy faster than baseline alternatives. We have also open-sourced our code at https://github.com/rajammanabrolu/KG-DQN.- Anthology ID:
- N19-1358
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Jill Burstein, Christy Doran, Thamar Solorio
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3557–3565
- Language:
- URL:
- https://aclanthology.org/N19-1358
- DOI:
- 10.18653/v1/N19-1358
- Cite (ACL):
- Prithviraj Ammanabrolu and Mark Riedl. 2019. Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3557–3565, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning (Ammanabrolu & Riedl, NAACL 2019)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/N19-1358.pdf
- Code
- rajammanabrolu/KG-DQN + additional community code