Tuning Models of Code with Compiler-Generated Reinforcement Learning Feedback.
Abhinav JainChima AdioleSwarat ChaudhuriThomas W. RepsChris JermainePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- probabilistic model
- case study
- statistical models
- dynamic programming
- machine learning
- general purpose
- relevance feedback
- reinforcement learning algorithms
- optimal control
- learning tasks
- statistical model
- complex systems
- software systems
- programming language
- state space
- prior knowledge
- artificial neural networks
- bayesian networks
- learning algorithm