paper-with-me

Papers

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

2018-01-18 · ACL 2018 7 · Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su

Training a task-completion dialogue agent via reinforcement learning (RL) is costly because it requires many interactions with real users. One common alternative is to use a user simulator. However, a user simulator usually lacks the language complexity of human interlocutors and the biases in its design may tend to degrade the agent. To address these issues, we present Deep Dyna-Q, which to our knowledge is the first deep RL framework that integrates planning for task-completion dialogue policy learning. We incorporate into the dialogue agent a model of the environment, referred to as the world model, to mimic real user response and generate simulated experience. During dialogue policy learning, the world model is constantly updated with real user experience to approach real user behavior, and in turn, the dialogue agent is optimized using both real experience and simulated experience. The effectiveness of our approach is demonstrated on a movie-ticket booking task in both simulated and human-in-the-loop settings.

📄 PDF Abstract BibTeX arXiv:1801.06176

Code (3)

MiuLab/DDQ 공식 구현 pytorch
para-zhou/RL_DDQ pytorch
sujoung/debuggedDDQ pytorch

Tasks

Reinforcement LearningReinforcement Learning (RL)Task-Completion Dialogue Policy Learning

Similar Papers 제목 키워드 기반

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

2018-11-19 · Yuexin Wu, Xiujun Li, Jingjing Liu, Jianfeng Gao 외

Training task-completion dialogue agents with reinforcement learning usually requires a large number of real user experiences. The Dyna-Q algorithm extends Q-learning by integrating a world model, and thus can effectivel…

Active LearningQ-LearningReinforcement LearningTask-Completion Dialogue Policy Learning

Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning

2018-08-28 · EMNLP 2018 10 · Shang-Yu Su, Xiujun Li, Jianfeng Gao, Jingjing Liu 외

This paper presents a Discriminative Deep Dyna-Q (D3Q) approach to improving the effectiveness and robustness of Deep Dyna-Q (DDQ), a recently proposed framework that extends the Dyna-Q algorithm to integrate planning fo…

Task-Completion Dialogue Policy Learning

Task-Completion Dialogue Policy Learning via Monte Carlo Tree Search with Dueling Network

2020-11-01 · EMNLP 2020 11 · Sihan Wang, Kaijie Zhou, Kunfeng Lai, Jianping Shen

We introduce a framework of Monte Carlo Tree Search with Double-q Dueling network (MCTS-DDU) for task-completion dialogue policy learning. Different from the previous deep model-based reinforcement learning methods, whic…

Model-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Task-Completion Dialogue Policy Learning

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

Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding

2026-08-06 · Xiaofeng Wang, Kakam Chong, Shuai Xiao, DeXin Kong 외 arxiv

Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination and rapid adaptation. Current methods often apply uniform goal-base…

Hierarchical Reinforcement Learning