Dialog Action-Aware Transformer for Dialog Policy Learning

CoRR(2023)

引用 0|浏览8
暂无评分
摘要
Recent works usually address Dialog policy learning DPL by training a reinforcement learning (RL) agent to determine the best dialog action. However, existing works on deep RL require a large volume of agent-user interactions to achieve acceptable performance. In this paper, we propose to make full use of the plain text knowledge from the pre-trained language model to accelerate the RL agent's learning speed. Specifically, we design a dialog action-aware transformer encoder (DaTrans), which integrates a new fine-tuning procedure named masked last action task to encourage DaTrans to be dialog-aware and distils action-specific features. Then, DaTrans is further optimized in an RL setting with ongoing interactions and evolves through exploration in the dialog action space toward maximizing long-term accumulated rewards. The effectiveness and efficiency of the proposed model are demonstrated with both simulator evaluation and human evaluation.
更多
查看译文
关键词
dialog policy learning,action-aware
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要