Fast Numerical Program Analysis with Reinforcement Learning.
Gagandeep SinghMarkus PüschelMartin T. VechevPublished in: CAV (1) (2018)
Keyphrases
- reinforcement learning
- function approximation
- database
- state space
- sensitivity analysis
- markov decision processes
- machine learning
- information retrieval
- direct policy search
- model free
- dynamic programming
- reinforcement learning methods
- artificial intelligence
- learning capabilities
- reinforcement learning algorithms
- control problems
- robotic control
- optimal policy
- numerical methods
- optimal control
- transfer learning
- level set
- supervised learning
- search space
- artificial neural networks
- genetic algorithm
- neural network