Papers with dialogue state search trees
Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models of reinforcement learning use background planning and may suffer from low-quality simulated experiences. |
| Approach: | They propose a Monte Carlo Tree Search with Double-q Dueling network framework for task-completion dialogue policy learning. |
| Outcome: | The proposed method outperforms the previous model-based reinforcement learning methods and is robust to simulation errors. |