Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations.
Yanwei WangNadia FigueroaShen LiAnkit ShahJulie ShahPublished in: CoRL (2022)
Keyphrases
- temporal logic
- imitation learning
- humanoid robot
- temporally extended
- model checking
- temporally extended goals
- modal logic
- classical planning
- image sequences
- verification method
- optimal policy
- human motion
- maximum margin
- linear temporal logic
- reinforcement learning
- belief revision
- multi modal
- robotic systems
- domain independent
- machine learning
- state space
- bayesian networks