Batch Policy Gradient Methods for Improving Neural Conversation Models

Kirthevasan Kandasamy, Yoram Bachrach, Ryota Tomioka, Daniel Tarlow, David Carter

Nov 04, 2016 (modified: Feb 10, 2017) ICLR 2017 conference submission readers: everyone
  • Abstract: We study reinforcement learning of chat-bots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chat-bot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous reinforcement learning work for natural language uses on-policy updates and/or is designed for on-line learning settings. We demonstrate empirically that such strategies are not appropriate for this setting and develop an off-policy batch policy gradient method (\bpg). We demonstrate the efficacy of our method via a series of synthetic experiments and an Amazon Mechanical Turk experiment on a restaurant recommendations dataset.
  • Keywords: Natural language processing, Reinforcement Learning
  • Conflicts:,,