Deep Imitative Reinforcement Learning for Temporal Logic Robot Motion Planning with Noisy Semantic Observations.
Qitong GaoMiroslav PajicMichael M. ZavlanosPublished in: ICRA (2020)
Keyphrases
- temporal logic
- reinforcement learning
- model checking
- modal logic
- concurrent systems
- satisfiability problem
- linear temporal logic
- verification method
- mazurkiewicz traces
- belief revision
- computation tree logic
- transition systems
- domain independent
- formal specification
- epistemic logic
- temporal knowledge
- bounded model checking
- model checker
- temporally extended
- dynamic constraints
- optimal policy
- state space
- knowledge representation
- multi agent