Decomposed Deep Q-Network for Coherent Task-Oriented Dialogue Policy Learning.
Yangyang ZhaoKai YinZhenyu WangMehdi DastaniShihan WangPublished in: IEEE ACM Trans. Audio Speech Lang. Process. (2024)
Keyphrases
- learning process
- learning algorithm
- reinforcement learning
- learning systems
- online learning
- connectionist networks
- dialogue system
- computer networks
- learning tasks
- supply chain
- active learning
- machine learning
- knowledge acquisition
- supervised learning
- complex networks
- learning problems
- wireless sensor networks
- inductive inference