Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games
Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, Ryuki Tachibana
Abstract
We show that Reinforcement Learning (RL) methods for solving Text-Based Games (TBGs) often fail to generalize on unseen games, especially in small data regimes. To address this issue, we propose Context Relevant Episodic State Truncation (CREST) for irrelevant token removal in observation text for improved generalization. Our method first trains a base model using Q-learning, which typically overfits the training games. The base model’s action token distribution is used to perform observation pruning that removes irrelevant tokens. A second bootstrapped model is then retrained on the pruned observation text. Our bootstrapped agent shows improved generalization in solving unseen TextWorld games, using 10x-20x fewer training games compared to previous state-of-the-art (SOTA) methods despite requiring fewer number of training episodes.- Anthology ID:
- 2020.emnlp-main.241
- Volume:
- Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3002–3008
- Language:
- URL:
- https://aclanthology.org/2020.emnlp-main.241
- DOI:
- 10.18653/v1/2020.emnlp-main.241
- Cite (ACL):
- Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, and Ryuki Tachibana. 2020. Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3002–3008, Online. Association for Computational Linguistics.
- Cite (Informal):
- Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games (Chaudhury et al., EMNLP 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.emnlp-main.241.pdf
- Code
- IBM/context-relevant-pruning-textrl