Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces.
Gellért WeiszPawel BudzianowskiPei-Hao SuMilica GasicPublished in: CoRR (2018)
Keyphrases
- action space
- reinforcement learning
- dialogue system
- continuous state
- state space
- markov decision processes
- state and action spaces
- real valued
- dynamic programming
- natural language
- stochastic processes
- machine learning
- mobile robot
- domain specific
- user interface
- cooperative
- function approximators
- spoken dialogue systems
- reinforcement learning methods
- control policies
- learning algorithm