JoTR: A Joint Transformer and Reinforcement Learning Framework for Dialog Policy Learning.
Wai-Chung KwanHuimin WangHongru WangZezhong WangXian WuYefeng ZhengKam-Fai WongPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- policy search
- sequential decision making
- optimal policy
- state space
- supervised learning
- learning problems
- learning scheme
- learning capabilities
- partially observable environments
- learning agents
- partially observable
- learning tasks
- action selection
- online learning
- model free reinforcement learning
- expert systems
- eligibility traces
- reinforcement learning problems
- dynamic programming
- continuous state spaces
- actor critic
- autonomous learning
- continuous state
- reinforcement learning methods
- power system
- state action
- robot control
- transfer learning