Papers by Ryuki Tachibana
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based Games (2020.emnlp-main)
Copied to clipboard
Subhajit Chaudhury, Daiki Kimura, Kartik Talamadupula, Michiaki Tatsubori, Asim Munawar, Ryuki Tachibana
| Challenge: | Reinforcement Learning methods for text-based games fail to generalize on unseen games, especially in small data regimes. |
| Approach: | They propose a Context Relevant Episodic State Truncation method for irrelevant token removal in observation text for improved generalization. |
| Outcome: | The proposed method shows that it can generalize on unseen games using 10x-20x fewer training games compared to previous state-of-the-art methods despite requiring fewer number of training episodes. |
Q-learning with Language Model for Edit-based Unsupervised Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Unsupervised text summarization methods are promising, but their performance is still behind that of state-of-the-art supervised methods. |
| Approach: | They propose a method based on Q-learning with an edit-based summarization that uses an Editorial Agent and Language Model converter to predict edit actions. |
| Outcome: | The proposed method delivers competitive performance even with zero paired data, while requiring no validation set. |