Synthesizing safe policies under probabilistic constraints with reinforcement learning and Bayesian model checking.
Lenz BelznerMartin WirsingPublished in: Sci. Comput. Program. (2021)
Keyphrases
- model checking
- reinforcement learning
- temporal logic
- optimal policy
- formal verification
- automated verification
- formal specification
- bayesian networks
- symbolic model checking
- finite state
- reachability analysis
- temporal properties
- model checker
- bounded model checking
- timed automata
- concurrent systems
- markov decision processes
- verification method
- epistemic logic
- partial observability
- computation tree logic
- asynchronous circuits
- transition systems
- process algebra
- formal methods
- partially observable markov decision processes
- constraint programming
- markov decision process
- multi agent
- reactive systems
- reward function
- reinforcement learning algorithms
- planning domains
- automated reasoning
- linear temporal logic
- dynamic programming