English

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

Artificial Intelligence 2017-11-21 v2 Computation and Language Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.1711.05715,
  title  = {BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems},
  author = {Zachary Lipton and Xiujun Li and Jianfeng Gao and Lihong Li and Faisal Ahmed and Li Deng},
  journal= {arXiv preprint arXiv:1711.05715},
  year   = {2017}
}

Comments

Duplicate of article already in the arXiv: arXiv:1608.05081

R2 v1 2026-06-22T22:47:12.671Z