paper-with-me

홈 › Papers

Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization

2023-05-05 · Yangyang Zhao, Zhenyu Wang, Mehdi Dastani, Shihan Wang

Training a dialogue policy using deep reinforcement learning requires a lot of exploration of the environment. The amount of wasted invalid exploration makes their learning inefficient. In this paper, we find and define an important reason for the invalid exploration: dead-ends. When a conversation enters a dead-end state, regardless of the actions taken afterward, it will continue in a dead-end trajectory until the agent reaches a termination state or maximum turn. We propose a dead-end resurrection (DDR) algorithm that detects the initial dead-end state in a timely and efficient manner and provides a rescue action to guide and correct the exploration direction. To prevent dialogue policies from repeatedly making the same mistake, DDR also performs dialogue data augmentation by adding relevant experiences containing dead-end states. We first validate the dead-end detection reliability and then demonstrate the effectiveness and generality of the method by reporting experimental results on several dialogue datasets from different domains.

📄 PDF Abstract BibTeX arXiv:2305.03262

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDeep Reinforcement LearningEfficient Exploration

Similar Papers 제목 키워드 기반

RescueBench: Can Embodied Agents Save Lives in the Wild ?

2026-06-01 · Kui Wu, Beiyu Guo, Hao Chen, ShuHang Xu 외 arxiv

Search-and-rescue (SAR) requires embodied agents to explore unfamiliar environments under multimodal uncertainty, perform multi-stage interactions, and retrieve spatial memory over long horizons. Existing benchmarks typi…

RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain

2023-06-06 · Sangeet Sagar, Mirco Ravanelli, Bernd Kiefer, Ivana Kruijff Korbayova 외

Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional speech in noisy and reverberant acoustic environments. This poses a particular c…

Decision MakingRobust Speech Recognitionspeech-recognitionSpeech Recognition

Safe Reinforcement Learning with Dead-Ends Avoidance and Recovery

2023-06-24 · Xiao Zhang, Hai Zhang, Hongtu Zhou, Chang Huang 외

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to a…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2

Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models

2024-07-02 · Annie S. Chen, Alec M. Lessing, Andy Tang, Govind Chada 외

Legged robots are physically capable of navigating a diverse variety of environments and overcoming a wide range of obstructions. For example, in a search and rescue mission, a legged robot could climb over debris, crawl…

Navigate

REX-RAG: Reasoning Exploration with Policy Correction in Retrieval-Augmented Generation

2025-08-11 · Wentao Jiang, Xiang Feng, Zengmao Wang, Yong Luo 외 arxiv

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generatio…

Reinforcement LearningDecision Making