Emotion-sensitive deep dyna-Q learning for task-completion dialogue policy learning.
Rui ZhangZhenyu WangMengdan ZhengYangyang ZhaoZhenhua HuangPublished in: Neurocomputing (2021)
Keyphrases
- learning algorithm
- reinforcement learning
- learning process
- function approximation
- temporal difference learning
- deep learning
- reinforcement learning methods
- optimal policy
- learning systems
- emotion recognition
- action selection
- rl algorithms
- state action
- affective states
- learning problems
- learning tasks
- monte carlo
- supervised learning
- state space
- cooperative