Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management
원문 초록
Deep reinforcement learning (RL) methods have significant potential for dialogue policy optimisation. However, they suffer from a poor performance in the early stages of learning. This is especially problematic for on-line learning with real users. Two approaches are introduced to tackle this problem. Firstly, to speed up the learning process, two sample-efficient neural networks algorithms: trust region actor-critic with experience replay (TRACER) and episodic natural actor-critic with experience replay (eNACER) are presented. For TRACER, the trust region helps to control the learning step size and avoid catastrophic model changes. For eNACER, the natural gradient identifies the steepest ascent direction in policy space to speed up the convergence. Both models employ off-policy learning with experience replay to improve sample-efficiency. Secondly, to mitigate the cold start issue, a corpus of demonstration data is utilised to pre-train the models prior to on-line reinforcement learning. Combining these two approaches, we demonstrate a practical approach to learn deep RL-based dialogue policies and demonstrate their effectiveness in a task-oriented information seeking domain.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints
Deep Reinforcement Learning with Gradient Eligibility Traces
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning
Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management
Developing a Chatbot system using Deep Learning based for Universities consultancy
토론
이 논문과 연결된 포럼 글이 아직 없습니다.