Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning.
Li ZhouKevin SmallYong ZhangSandeep AtluriPublished in: CoRR (2021)
Keyphrases
- imitation learning
- reinforcement learning
- question answer pairs
- maximum margin
- humanoid robot
- question answering
- robotic systems
- function approximation
- reinforcement learning methods
- state space
- machine learning
- model free
- mobile robot
- reward function
- co occurrence
- graphical models
- multi modal
- supervised learning
- reinforcement learning algorithms
- support vector
- artificial intelligence