Sample-efficient Deep Reinforcement Learning for Dialog Control.
Kavosh AsadiJason D. WilliamsPublished in: CoRR (2016)
Keyphrases
- reinforcement learning
- robot control
- optimal control
- machine learning
- function approximation
- control strategy
- control system
- computationally expensive
- control theory
- real time
- learning problems
- cost effective
- lightweight
- supervised learning
- state space
- mobile robot
- learning process
- user interface
- multi agent
- training data
- case study