Zombori, Zsolt and Csiszárik, Adrián and Henryk, Michalewski and Cezary, Kaliszyk and and, Josef Urban (2019) Curriculum learning and theorem proving. In: Fourth Conference on Artificial Intelligence and Theorem Proving AITP 2019, 2019.04.07-2019.04.12, Obergurgl.
|
Text
paper13-2.pdf Download (180kB) | Preview |
Abstract
We propose a proof guidance approach for ATP systems based on reinforcement learning (RL). Unlike previous approaches, we specifically target long proofs, i.e., our aim is to be able to find proofs that are hundreds or even thousands of steps long.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Q Science / természettudomány > QA Mathematics / matematika |
| SWORD Depositor: | MTMT SWORD |
| Depositing User: | MTMT SWORD |
| Date Deposited: | 29 Sep 2026 11:24 |
| Last Modified: | 29 Sep 2026 11:24 |
| URI: | https://real.mtak.hu/id/eprint/247930 |
Actions (login required)
 |
View Item |
