Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tian, Chang, Yin, Wenpeng, Moens, Marie-Francine
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911837766811648
author Tian, Chang
Yin, Wenpeng
Moens, Marie-Francine
author_facet Tian, Chang
Yin, Wenpeng
Moens, Marie-Francine
contents A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action decisions rely on an accurate estimation of action values. The overestimation problem is a widely known issue of RL since its estimate of the maximum action value is larger than the ground truth, which results in an unstable learning process and suboptimal policy. This problem is detrimental to RL-based dialogue policy learning. To mitigate this problem, this paper proposes a dynamic partial average estimator (DPAV) of the ground truth maximum action value. DPAV calculates the partial average between the predicted maximum action value and minimum action value, where the weights are dynamically adaptive and problem-dependent. We incorporate DPAV into a deep Q-network as the dialogue policy and show that our method can achieve better or comparable results compared to top baselines on three dialogue datasets of different domains with a lower computational load. In addition, we also theoretically prove the convergence and derive the upper and lower bounds of the bias compared with those of other methods.
format Preprint
id arxiv_https___arxiv_org_abs_2207_11762
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System
Tian, Chang
Yin, Wenpeng
Moens, Marie-Francine
Computation and Language
Artificial Intelligence
A dialogue policy module is an essential part of task-completion dialogue systems. Recently, increasing interest has focused on reinforcement learning (RL)-based dialogue policy. Its favorable performance and wise action decisions rely on an accurate estimation of action values. The overestimation problem is a widely known issue of RL since its estimate of the maximum action value is larger than the ground truth, which results in an unstable learning process and suboptimal policy. This problem is detrimental to RL-based dialogue policy learning. To mitigate this problem, this paper proposes a dynamic partial average estimator (DPAV) of the ground truth maximum action value. DPAV calculates the partial average between the predicted maximum action value and minimum action value, where the weights are dynamically adaptive and problem-dependent. We incorporate DPAV into a deep Q-network as the dialogue policy and show that our method can achieve better or comparable results compared to top baselines on three dialogue datasets of different domains with a lower computational load. In addition, we also theoretically prove the convergence and derive the upper and lower bounds of the bias compared with those of other methods.
title Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2207.11762