Incremental on-line adaptation of POMDP-based dialogue managers to extended domains.
Milica GasicDongho KimPirros TsiakoulisCatherine BreslinMatthew HendersonMartin SzummerBlaise ThomsonSteve J. YoungPublished in: INTERSPEECH (2014)
Keyphrases
- application domains
- reinforcement learning
- information technology
- man machine
- decision making
- dynamical systems
- incremental learning
- finite state
- machine learning
- human machine
- mixed initiative
- partially observable markov decision processes
- state space
- belief state
- real world
- belief space
- end user computing
- dialogue management
- interactive question answering