Concurrent Reinforcement Learning from Customer Interactions.
David SilverLeonard NewnhamDavid BarkerSuzanne WellerJason McFallPublished in: ICML (3) (2013)
Keyphrases
- reinforcement learning
- multi agent
- electronic commerce
- hierarchical reinforcement learning
- learning algorithm
- model free
- function approximation
- optimal policy
- markov decision processes
- state space
- reinforcement learning algorithms
- machine learning
- action selection
- customer behavior
- potential customers
- website
- purchase behavior
- robotic control
- learning classifier systems
- customer satisfaction
- customer service
- policy search
- customer knowledge