Program Synthesis Using Deduction-Guided Reinforcement Learning.
Yanju ChenChenglong WangOsbert BastaniIsil DilligYu FengPublished in: CAV (2) (2020)
Keyphrases
- program synthesis
- reinforcement learning
- function approximation
- recursive programs
- state space
- reinforcement learning algorithms
- learning algorithm
- optimal policy
- markov decision processes
- theorem proving
- action selection
- inference rules
- model free
- low level
- supervised learning
- transfer learning
- learning problems
- inductive logic programming
- learning process