Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning.
Yunke WangBo DuChang XuPublished in: AAAI (2023)
Keyphrases
- imitation learning
- reinforcement learning
- maximum margin
- robotic systems
- humanoid robot
- semi supervised learning
- labeled data
- unsupervised learning
- unlabeled data
- training data
- supervised learning
- active learning
- real time
- multi modal
- multi agent
- data points
- background knowledge
- prior knowledge
- reinforcement learning methods