arXiv:1711.05715
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems
원문 초록
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as \epsilon-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task Independent Capsule-Based Agents for Deep Q-Learning
Deep Reinforcement Learning Based Power Allocation for D2D Network
Deep Reinforcement Learning with Gradient Eligibility Traces
Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty
Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access
토론
이 논문과 연결된 포럼 글이 아직 없습니다.