Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2022, 1, pp. 538-560
- Issue Date:
- 2022-01-01
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Text-based games provide an interactive way to study natural language processing. While deep reinforcement learning has shown effectiveness in developing the game playing agent, the low sample efficiency and the large action space remain to be the two major challenges that hinder the DRL from being applied in the real world. In this paper, we address the challenges by introducing world-perceiving modules, which automatically decompose tasks and prune actions by answering questions about the environment. We then propose a two-phase training framework to decouple language learning from reinforcement learning, which further improves the sample efficiency. The experimental results show that the proposed method significantly improves the performance and sample efficiency. Besides, it shows robustness against compound error and limited pre-training data.
Please use this identifier to cite or link to this item: