paper-with-me

홈 › Papers

Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning

2017-09-01 · EMNLP 2017 9 · Lu Chen, Xiang Zhou, Cheng Chang, Runzhe Yang, Kai Yu

Hand-crafted rules and reinforcement learning (RL) are two popular choices to obtain dialogue policy. The rule-based policy is often reliable within predefined scope but not self-adaptable, whereas RL is evolvable with data but often suffers from a bad initial performance. We employ a \textit{companion learning} framework to integrate the two approaches for \textit{on-line} dialogue policy learning, in which a pre-defined rule-based policy acts as a {``}teacher{''} and guides a data-driven RL system by giving example actions as well as additional rewards. A novel \textit{agent-aware dropout} Deep Q-Network (AAD-DQN) is proposed to address the problem of when to consult the teacher and how to learn from the teacher{'}s experiences. AAD-DQN, as a data-driven student policy, provides (1) two separate experience memories for student and teacher, (2) an uncertainty estimated by dropout to control the timing of consultation and learning. Simulation experiments showed that the proposed approach can significantly improve both \textit{safety}and \textit{efficiency} of on-line policy optimization compared to other companion learning approaches as well as supervised pre-training using static dialogue corpus.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech Recognition (ASR)Dialogue ManagementReinforcement LearningReinforcement Learning (RL)Speech RecognitionSpoken Dialogue SystemsSpoken Language Understanding

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

2026-06-02 · Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield 외 arxiv

Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems, demand reliable hazard identification. While large language models (LLMs) have shown promise in autom…

A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation

2026-03-31 · Ha Na Cho arxiv

Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated mul…

Using In-Context Learning to Improve Dialogue Safety

2023-02-02 · Nicholas Meade, Spandana Gella, Devamanyu Hazarika, Prakhar Gupta 외

While large neural-based conversational models have become increasingly proficient dialogue agents, recent work has highlighted safety issues with these systems. For example, these systems can be goaded into generating t…

In-Context LearningRe-RankingRetrieval

Disruptive Talk Detection in Multi-Party Dialogue within Collaborative Learning Environments with a Regularized User-Aware Network

2022-09-01 · SIGDIAL (ACL) 2022 9 · Kyungjin Park, Hyunwoo Sohn, Wookhee Min, Bradford Mott 외

Accurate detection and appropriate handling of disruptive talk in multi-party dialogue is essential for users to achieve shared goals. In collaborative game-based learning environments, detecting and attending to disrupt…

Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models

2025-06-28 · Younwoo Choi, Changling Li, Yongjin Yang, Zhijing Jin

As large language models (LLMs) are increasingly integrated into multi-agent and human-AI systems, understanding their awareness of both self-context and conversational partners is essential for ensuring reliable perform…