Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness
This work addresses the challenge of improving dialogue agents in interactive scenarios by incorporating awareness of the opposite agent's behavior, which is incremental but practically relevant for real-world applications.
The paper tackles the problem of goal-oriented dialogue policy learning by proposing a framework that estimates and utilizes the opposite agent's policy, rather than treating it as part of the environment. The model shows superior performance over state-of-the-art baselines on both cooperative and competitive dialogue tasks.
Most existing approaches for goal-oriented dialogue policy learning used reinforcement learning, which focuses on the target agent policy and simply treat the opposite agent policy as part of the environment. While in real-world scenarios, the behavior of an opposite agent often exhibits certain patterns or underlies hidden policies, which can be inferred and utilized by the target agent to facilitate its own decision making. This strategy is common in human mental simulation by first imaging a specific action and the probable results before really acting it. We therefore propose an opposite behavior aware framework for policy learning in goal-oriented dialogues. We estimate the opposite agent's policy from its behavior and use this estimation to improve the target agent by regarding it as part of the target policy. We evaluate our model on both cooperative and competitive dialogue tasks, showing superior performance over state-of-the-art baselines.