DORA: Toward Policy Optimization for Task-oriented Dialogue System with Efficient Context

2021-07-07 · Hyunmin Jeon, Gary Geunbae Lee

Recently, reinforcement learning (RL) has been applied to task-oriented dialogue systems by using latent actions to solve shortcomings of supervised learning (SL). In this paper, we propose a multi-domain task-oriented dialogue system, called Dialogue System with Optimizing a Recurrent Action Policy using Efficient Context (DORA), that uses SL, with subsequently applied RL to optimize dialogue systems using a recurrent dialogue policy. This dialogue policy recurrently generates explicit system actions as a both word-level and high-level policy. As a result, DORA is clearly optimized during both SL and RL steps by using an explicit system action policy that considers an efficient context instead of the entire dialogue history. The system actions are both interpretable and controllable, whereas the latent actions are not. DORA improved the success rate by 6.6 points on MultiWOZ 2.0 and by 10.9 points on MultiWOZ 2.1.

📄 PDF Abstract BibTeX arXiv:2107.03286

Code (2)

budzianowski/multiwoz 공식 구현 pytorch

MindSpore-scientific-2/code-5/tree/main/dora mindspore

Tasks

Reinforcement Learning (RL)Task-Oriented Dialogue Systems

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning

2017-11-29 · Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah 외

In this paper, we present a neural network based task-oriented dialogue system that can be optimized end-to-end with deep reinforcement learning (RL). The system is able to track dialogue state, interface with knowledge …

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks

2025-11-17 · Hui Wang, Fafa Zhang, Xiaoyu Zhang, Chaoxu Mu arxiv

In goal-oriented dialogue tasks, the main challenge is to steer the interaction towards a given goal within a limited number of turns. Existing approaches either rely on elaborate prompt engineering, whose effectiveness …

Prompt Engineering

Generative Dialog Policy for Task-oriented Dialog Systems

2019-09-17 · Tian Lan, Xian-Ling Mao, He-Yan Huang

There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue poli…

General Classification Task-Oriented Dialogue Systems

Deep Reinforcement Learning for On-line Dialogue State Tracking

2020-09-22 · Zhi Chen, Lu Chen, Xiang Zhou, Kai Yu

Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching b…

Deep Reinforcement Learning Dialogue Management Dialogue State Tracking Management+4

An Efficient Task-Oriented Dialogue Policy: Evolutionary Reinforcement Learning Injected by Elite Individuals

2025-06-04 · Yangyang Zhao, Ben Niu, Libo Qin, Shihan Wang

Deep Reinforcement Learning (DRL) is widely used in task-oriented dialogue systems to optimize dialogue policy, but it struggles to balance exploration and exploitation due to the high dimensionality of state and action …

Deep Reinforcement Learning Evolutionary Algorithms Task-Oriented Dialogue Systems