Towards Scalable Verification of Deep Reinforcement Learning.
Guy AmirMichael SchapiraGuy KatzPublished in: FMCAD (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- model checking
- model free
- optimal policy
- formal methods
- formal verification
- reinforcement learning algorithms
- temporal difference learning
- temporal difference
- verification method
- learning algorithm
- markov decision processes
- machine learning
- web scale
- memory efficient
- false acceptance
- cryptographic protocols
- data sets
- optimal control
- supervised learning
- learning process
- multi agent
- bayesian networks
- e learning
- neural network