{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-reason-in-large-theories-without","title":"Learning to Reason in Large Theories without Imitation","arxiv_id":"1905.10501","date":"2019-05-25","proceeding":null,"authors":["Kshitij Bansal","Christian Szegedy","Markus N. Rabe","Sarah M. Loos","Viktor Toman"],"abstract":"In this paper, we demonstrate how to do automated theorem proving in the presence of a large knowledge base of potential premises without learning from human proofs. We suggest an exploration mechanism that mixes in additional premises selected by a tf-idf (term frequency-inverse document frequency) based lookup in a deep reinforcement learning scenario. This helps with exploring and learning which premises are relevant for proving a new theorem. Our experiments show that the theorem prover trained with this exploration mechanism outperforms provers that are trained only on human proofs. It approaches the performance of a prover trained by a combination of imitation and reinforcement learning. We perform multiple experiments to understand the importance of the underlying assumptions that make our exploration approach work, thus explaining our design choices.","url_abs":"https://arxiv.org/abs/1905.10501v3","url_pdf":"https://arxiv.org/pdf/1905.10501v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"automated-theorem-proving","task_name":"Automated Theorem Proving"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/automated-theorem-proving-on-holist-benchmark","task":"Automated Theorem Proving","dataset":"HOList benchmark","model":"BoW2 (extra -ves)","rank_in_archive_order":3,"of":4,"metrics":{"Percentage correct":"36.55"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.10501","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}