A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis.
Joseph PalermoJohnny YeAlok SinghPublished in: CoRR (2021)
Keyphrases
- program synthesis
- learning environment
- recursive programs
- human reasoning
- knowledge base
- reinforcement learning
- learning process
- e learning
- inductive logic programming
- learning outcomes
- learning activities
- mathematical proofs
- learning systems
- artificial intelligence
- reasoning process
- information extraction
- structured data
- object oriented
- knowledge representation
- low level
- computer algebra systems