End-to-End Offline Goal-Oriented Dialog Policy Learning via Policy Gradient.
Li ZhouKevin SmallOleg RokhlenkoCharles ElkanPublished in: CoRR (2017)
Keyphrases
- end to end
- policy gradient
- goal oriented
- learning algorithm
- model free reinforcement learning
- actor critic
- admission control
- learning process
- learning problems
- policy gradient methods
- learning tasks
- reinforcement learning
- adaptive control
- function approximation
- gradient method
- state action
- evaluation function
- domain independent
- supervised learning
- multi agent systems