Using Reinforcement Learning to Model Incrementality in a Fast-Paced Dialogue Game

Abstract

We apply Reinforcement Learning (RL) to the problem of incremental dialogue policy learning in the context of a fast-paced dialogue game. We compare the policy learned by RL with a high performance baseline policy which has been shown to perform very efficiently (nearly as well as humans) in this dialogue game. The RL policy outperforms the baseline policy in offline simulations (based on real user data). We provide a detailed comparison of the RL policy and the baseline policy, including information about how much effort and time it took to develop each one of them. We also highlight the cases where the RL policy performs better, and show that understanding the RL policy can provide valuable insights which can inform the creation of an even better rule-based policy.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2017
Accession Number
AD1160054

Entities

People

  • David Devault
  • Kallirroi Georgila
  • Ramesh Manuvinakurike

Organizations

  • University of Southern California

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Automated Speech Recognition
  • Computational Linguistics
  • Computational Science
  • Computer Languages
  • Dialogue Systems
  • Language
  • Learning
  • Linguistics
  • Natural Language Processing
  • Natural Languages
  • Recognition
  • Reinforcement Learning
  • Simulations
  • Test Sets
  • Training
  • United States

Readers

  • East Asian Political and Security Studies within the Soviet Union
  • Neural Network Machine Learning.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.

Technology Areas

  • AI & ML