Tractable Reinforcement Learning for Signal Temporal Logic Tasks With Counterfactual Experience Replay.
Siqi WangXunyuan YinShaoyuan LiXiang YinPublished in: IEEE Control. Syst. Lett. (2024)
Keyphrases
- temporal logic
- reinforcement learning
- model checking
- modal logic
- concurrent systems
- satisfiability problem
- verification method
- belief revision
- linear temporal logic
- computation tree logic
- state space
- multi agent
- learning algorithm
- model checker
- mazurkiewicz traces
- formal specification language
- bounded model checking
- dynamic constraints
- np complete
- dynamical systems
- video sequences
- automata theoretic
- domain specific