Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative
This work addresses a specific problem in dialog systems for developers, offering an incremental improvement by replacing adversarial learning with a more stable alternative.
The paper tackles the challenge of manually constructing fine-grained rewards for dialog policy learning in multi-domain task-oriented scenarios by analyzing adversarial learning's role and proposing an alternative method that eliminates it while retaining advantages, achieving evaluation on the MultiWOZ corpus.
Dialog policies, which determine a system's action based on the current state at each dialog turn, are crucial to the success of the dialog. In recent years, reinforcement learning (RL) has emerged as a promising option for dialog policy learning (DPL). In RL-based DPL, dialog policies are updated according to rewards. The manual construction of fine-grained rewards, such as state-action-based ones, to effectively guide the dialog policy is challenging in multi-domain task-oriented dialog scenarios with numerous state-action pair combinations. One way to estimate rewards from collected data is to train the reward estimator and dialog policy simultaneously using adversarial learning (AL). Although this method has demonstrated superior performance experimentally, it is fraught with the inherent problems of AL, such as mode collapse. This paper first identifies the role of AL in DPL through detailed analyses of the objective functions of dialog policy and reward estimator. Next, based on these analyses, we propose a method that eliminates AL from reward estimation and DPL while retaining its advantages. We evaluate our method using MultiWOZ, a multi-domain task-oriented dialog corpus.