Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking.
Dennis GrossThiago D. SimãoNils JansenGuillermo A. PérezPublished in: ICAART (3) (2023)
Keyphrases
- model checking
- reinforcement learning
- optimal policy
- temporal logic
- markov decision process
- multi agent
- state space
- formal specification
- automated verification
- formal verification
- finite state
- reward function
- partial order reduction
- temporal properties
- partially observable markov decision processes
- markov decision processes
- markov decision problems
- model checker
- finite state machines
- reachability analysis
- bounded model checking
- decision problems
- timed automata
- process algebra
- verification method
- symbolic model checking
- computation tree logic
- transition systems
- dynamic programming
- infinite horizon
- concurrent systems
- pspace complete
- epistemic logic
- reinforcement learning algorithms
- reactive systems
- learning algorithm
- linear temporal logic
- asynchronous circuits
- petri net
- alternating time temporal logic