Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning.
Gil LedermanMarkus N. RabeSanjit A. SeshiaPublished in: CoRR (2018)
Keyphrases
- function approximation
- reinforcement learning
- learning tasks
- automated reasoning
- function approximators
- learning algorithm
- learning problems
- temporal difference
- supervised learning
- reinforcement learning algorithms
- search algorithm
- action selection
- learning process
- constraint satisfaction problems
- optimal policy
- probabilistic reasoning