Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access

2016-09-03 · ACL 2017 7 · Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng

This paper proposes KB-InfoBot -- a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to access real-world knowledge. Previous systems achieved this by issuing a symbolic query to the KB to retrieve entries based on their attributes. However, such symbolic operations break the differentiability of the system and prevent end-to-end training of neural dialogue agents. In this paper, we address this limitation by replacing symbolic queries with an induced "soft" posterior distribution over the KB that indicates which entities the user is interested in. Integrating the soft retrieval process with a reinforcement learner leads to higher task success rate and reward in both simulations and against real users. We also present a fully neural end-to-end agent, trained entirely from user feedback, and discuss its application towards personalized dialogue agents. The source code is available at https://github.com/MiuLab/KB-InfoBot.

📄 PDF Abstract BibTeX arXiv:1609.00777

Code (1)

MiuLab/KB-InfoBot 공식 구현

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)RetrievalWorld Knowledge

Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue

2021-07-12 · Zipeng Xu, Fandong Meng, Xiaojie Wang, Duo Zheng 외

To encourage AI agents to conduct meaningful Visual Dialogue (VD), the use of Reinforcement Learning has been proven potential. In Reinforcement Learning, it is crucial to represent states and assign rewards based on the…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Knowledge acquisition for dialogue agents using reinforcement learning on graph representations

2024-06-27 · Selene Baez Santamaria, Shihan Wang, Piek Vossen

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent model…

CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning

2022-04-18 · NAACL 2022 7 · Siddharth Verma, Justin Fu, Mengjiao Yang, Sergey Levine

Conventionally, generation of natural language for dialogue agents may be viewed as a statistical learning problem: determine the patterns in human-provided data and generate appropriate responses with similar statistica…

Chatbot Offline RL reinforcement-learning Reinforcement Learning+1

A User Simulator for Task-Completion Dialogues

2016-12-17 · Xiujun Li, Zachary C. Lipton, Bhuwan Dhingra, Lihong Li 외

Despite widespread interests in reinforcement-learning for task-oriented dialogue systems, several obstacles can frustrate research and development progress. First, reinforcement learners typically require interaction wi…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Task-Oriented Dialogue Systems+1

Deep Reinforcement Learning for Dialogue Generation

2016-06-05 · EMNLP 2016 11 · Jiwei Li, Will Monroe, Alan Ritter, Michel Galley 외

Recent neural models of dialogue generation offer great promise for generating responses for conversational agents, but tend to be shortsighted, predicting utterances one at a time while ignoring their influence on futur…

Chatbot Deep Reinforcement Learning Dialogue Generation Diversity+4