Bayesian reinforcement learning for POMDP-based dialogue systems.
ShaoWei PngJoelle PineauPublished in: ICASSP (2011)
Keyphrases
- bayesian reinforcement learning
- dialogue system
- partially observable markov decision processes
- optimal policy
- reinforcement learning
- monte carlo tree search
- natural language
- finite state
- decision problems
- spoken dialogue systems
- mixed initiative
- state space
- markov decision processes
- tutorial dialogue
- dynamical systems
- multi agent
- markov decision problems
- dynamic programming
- planning under uncertainty
- machine learning
- belief state
- infinite horizon
- monte carlo
- partially observable markov decision process
- human users
- user model
- policy iteration
- function approximation
- particle filter
- data mining