Verifiable and Interpretable Reinforcement Learning through Program Synthesis.
Abhinav VermaPublished in: AAAI (2019)
Keyphrases
- program synthesis
- reinforcement learning
- function approximation
- learning algorithm
- temporal difference
- recursive programs
- inductive logic programming
- markov decision processes
- state space
- sufficient conditions
- machine learning
- learning process
- model free
- reinforcement learning algorithms
- transfer learning
- learning problems
- multi agent
- web pages
- low level
- active learning
- database
- database systems
- action selection
- artificial intelligence