arXiv:1711.05715

BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems

Zachary Lipton, Xiujun Li, Jianfeng Gao, Lihong Li, Faisal Ahmed, Li Deng

제출 2017-11-15

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.

토론

이 논문과 연결된 포럼 글이 아직 없습니다.