Model-based reinforcement learning for approximate optimal control with temporal logic specifications.
Max H. CohenCalin BeltaPublished in: HSCC (2021)
Keyphrases
- optimal control
- temporal logic
- model based reinforcement learning
- concurrent systems
- model checking
- transition systems
- reinforcement learning
- model checker
- reactive systems
- bounded model checking
- markov decision processes
- dynamic programming
- formal specification language
- formal specification
- modal logic
- control strategy
- infinite horizon
- linear temporal logic
- finite state
- optimal control problems
- formal verification
- average cost
- belief revision
- utility function
- optimal policy
- machine learning