Reduced variance deep reinforcement learning with temporal logic specifications.
Qitong GaoDavood HajinezhadYan ZhangYiannis KantarosMichael M. ZavlanosPublished in: ICCPS (2019)
Keyphrases
- temporal logic
- reinforcement learning
- concurrent systems
- model checking
- transition systems
- bounded model checking
- reactive systems
- model checker
- formal specification language
- modal logic
- satisfiability problem
- formal specification
- linear temporal logic
- verification method
- formal verification
- predicate logic
- mazurkiewicz traces
- temporal knowledge
- epistemic logic
- state space
- belief revision
- computation tree logic
- multi agent
- dynamic constraints
- description language
- inference rules
- domain specific