Reinforcement Learning for Guiding the E Theorem Prover.
Jack McKeownGeoff SutcliffePublished in: FLAIRS (2023)
Keyphrases
- theorem prover
- reinforcement learning
- theorem proving
- automated reasoning
- first order logic
- automated theorem proving
- term rewriting
- inference rules
- function approximation
- automated deduction
- natural deduction
- computer algebra
- higher order logic
- formal semantics
- boolean algebra
- learning algorithm
- temporal difference
- reinforcement learning algorithms
- model free
- multi agent
- mathematical knowledge
- proof search
- timed automata
- formal proof
- learning process
- markov decision processes
- higher order
- supervised learning
- state space