JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialogue Policy Learning.
Wai-Chung KwanHuimin WangHongru WangZezhong WangBin LiangXian WuYefeng ZhengKam-Fai WongPublished in: LREC/COLING (2024)
Keyphrases
- reinforcement learning
- learning process
- action selection
- learning algorithm
- supervised learning
- learning problems
- sequential decision making
- learning scheme
- autonomous learning
- function approximation
- fuzzy logic
- policy search
- active exploration
- function approximators
- learning capabilities
- multi task
- learning systems
- online learning
- continuous state and action spaces
- multi agent
- model free reinforcement learning
- continuous state spaces
- actor critic
- rl algorithms
- reinforcement learning methods
- partially observable
- learning tasks