Reinforcement Learning for Syntax-Guided Synthesis.
Julian ParsertElizabeth PolgreenPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- program synthesis
- state space
- optimal policy
- learning capabilities
- model free
- database
- markov decision processes
- robotic control
- reinforcement learning algorithms
- action selection
- high level
- machine learning
- sufficient conditions
- learning classifier systems
- least squares
- search space
- search algorithm
- information retrieval
- markov decision process
- multi agent reinforcement learning
- data mining