Abstract: BanditFuzz: A Reinforcement-Learning based Performance Fuzzer for SMT Solvers.
Joseph ScottFederico MoraVijay GaneshPublished in: SMT (2020)
Keyphrases
- reinforcement learning
- modulo theories
- state space
- function approximation
- learning algorithm
- statistical machine translation
- reinforcement learning algorithms
- reinforcement learning methods
- machine learning
- transfer learning
- optimal policy
- model free
- temporal difference
- multi agent
- temporal abstractions
- robotic control
- high level
- multi agent reinforcement learning