Extrapolation of an Optimal Policy using Statistical Probabilistic Model Checking.
Artur RatajBozena Wozna-SzczesniakPublished in: CS&P (2016)
Keyphrases
- model checking
- optimal policy
- finite state
- temporal logic
- markov decision processes
- state space
- finite horizon
- decision problems
- state dependent
- reinforcement learning
- temporal properties
- formal specification
- long run
- automated verification
- dynamic programming
- infinite horizon
- symbolic model checking
- sufficient conditions
- verification method
- bayesian networks
- formal verification
- transition systems
- model checker
- bounded model checking
- computation tree logic
- average cost
- markov decision process
- formal methods
- reward function
- policy iteration
- epistemic logic
- alternating time temporal logic
- initial state
- partially observable markov decision processes
- lost sales
- binary decision diagrams
- markov decision problems
- queueing networks
- modal logic
- probabilistic model
- computational complexity
- search algorithm