Learning dialogue policies using state aggregation in reinforcement learning.
Matthias DeneckeKohji DohsakaMikio NakanoPublished in: INTERSPEECH (2004)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- state space
- optimal policy
- reinforcement learning agents
- learning systems
- state action
- macro actions
- policy search
- learning tasks
- online learning
- learning problems
- learning capabilities
- dynamical systems
- reinforcement learning methods
- actor critic
- hierarchical reinforcement learning
- active learning
- natural language