Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning.
Deborah CohenMoonkyung RyuYinlam ChowOrgad KellerIdo GreenbergAvinatan HassidimMichael FinkYossi MatiasIdan SzpektorCraig BoutilierGal ElidanPublished in: CoRR (2022)
Keyphrases
- open ended
- spoken dialogue
- reinforcement learning
- mixed initiative
- learning outcomes
- affect detection
- dynamic environments
- dialogue management
- function approximation
- inquiry learning
- action selection
- partially observable
- multiple choice
- markov decision processes
- social interaction
- dialogue system
- reinforcement learning algorithms
- spoken dialogue systems
- multi agent
- e learning