Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness

TL;DR

This paper introduces a novel framework for goal-oriented dialogue policy learning that estimates and leverages the opposite agent's behavior, leading to improved performance in both cooperative and competitive tasks.

Contribution

It proposes an opposite behavior aware framework that infers the opposite agent's policy and integrates it into the target agent's decision-making process.

Findings

Outperforms state-of-the-art baselines in dialogue tasks

Effective in both cooperative and competitive scenarios

Demonstrates the value of modeling opposite agent behavior

Abstract

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.