Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations.
Sangwon SeoVaibhav V. UnhelkarPublished in: IJCAI (2022)
Keyphrases
- imitation learning
- semi supervised
- reinforcement learning
- humanoid robot
- semi supervised learning
- labeled data
- robotic systems
- maximum margin
- pairwise
- optimal policy
- supervised learning
- unlabeled data
- active learning
- graphical models
- markov decision process
- reinforcement learning methods
- support vector
- markov decision processes
- video sequences
- high dimensional
- real time