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.

提出了一种新的探索算法，基于 Bayes-by-Backprop 神经网络和重放缓冲区，可以大大提高深度 Q 学习在对话系统中的效率并比传统的探索策略学习得更快。

任务导向对话系统中深度强化学习的高效探索

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

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.

该研究提出了一种新算法，通过 Thompson 采样和 Bayes-by-Backprop 神经网络，可以显著提高深度 Q 学习代理在对话系统中的探索效率，并表明混合已成功经历的 episode 的回放池可以使 Q 学习成为可能。