Rescue Conversations from Dead-ends: Efficient Exploration for Task-oriented Dialogue Policy Optimization
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
When Can Learned Uncertainty Be Trusted? An Audit of Distributional Reinforcement Learning
보상 인플레이션: 강화학습을 위한 건강한 자극
Reward Inflation: A Healthy Stimulus for Reinforcement Learning
로봇 행동을 위한 fNIRS 기반 오프라인 강화학습 접근법
An offline approach to fNIRS-guided reinforcement learning for robot behavior
베이지안 내쉬를 넘어서: 비대칭 정보 하의 적대적 팀 게임을 위한 미니맥스-후회 균형 학습
Beyond Bayesian Nash: Learning Minimax-Regret Equilibria for Adversarial Team Games under Asymmetric Information
VIGOR: 모델 기반 강화학습에서 잠재 공간 일관성을 통한 제로샷 시각적 일반화
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
Ocular Verification for Virtual Reality
토론
이 논문과 연결된 포럼 글이 아직 없습니다.