Feudal Reinforcement Learning for Dialogue Management in Large Domains.
Iñigo CasanuevaPawel BudzianowskiPei-Hao SuStefan UltesLina Maria Rojas-BarahonaBo-Hsiang TsengMilica GasicPublished in: CoRR (2018)
Keyphrases
- dialogue management
- reinforcement learning
- learning agent
- dialogue system
- spoken dialogue systems
- transfer learning
- language understanding
- function approximation
- natural language generation
- state space
- partially observable markov decision process
- learning algorithm
- markov decision processes
- cross domain
- machine learning
- optimal policy
- knowledge acquisition