Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications.
Krishna Chaitanya KalagarlaRahul JainPierluigi NuzzoPublished in: CoRR (2021)
Keyphrases
- optimal control
- temporal logic
- model checking
- concurrent systems
- transition systems
- model free reinforcement learning
- bounded model checking
- reactive systems
- policy gradient
- model checker
- formal specification language
- reinforcement learning
- control problems
- dynamic programming
- formal specification
- control strategy
- infinite horizon
- formal verification
- computation tree logic
- verification method
- optimal control problems
- linear temporal logic
- formal methods
- stochastic processes
- real time
- finite state
- control law
- mathematical model
- linear programming
- multi agent systems
- neural network