Reinforcement Learning of Theorem Proving

Cezary Kaliszyk, Josef Urban, Henryk Michalewski, Miroslav Olšák

Neural Information Processing Systems 

In practice, today's best ATP system are however still far weaker than trained mathematicians in most research domains. Machine learning from many proofs could be used to improveonthis.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found