2026-09-19T02:43:55Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1242452026-06-06T00:48:43Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Tomaso Poggio. Guo, Hairuo. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2020-03-24T15:36:07Z 2020-03-24T15:36:07Z 2019 2019 https://hdl.handle.net/1721.1/124245 1145019864 This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019 Cataloged from student-submitted PDF version of thesis. Includes bibliographical references (pages 37-38). Despite recent advances in reinforcement learning (RL) that have allowed AI algorithms to master games such as Go from scratch, scant progress has been made on applying RL to one of the first tasks seen as susceptible to automation: theorem proving. I present steps towards training agents to construct proofs through utilizing the ability to pose hypotheses as a way to uncover information and break tasks down into subtasks. To do so, I create a novel bitstring problem that retains many of the challenges posed by proof construction while dispensing with the need to parse grammars. I then assess the performance of well-known RL algorithms on tasks derived from this problem, demonstrating that it is non-trivial. Finally, I alter a model that successfully learns one of the bitstring tasks in order to acquire results on possible mechanisms for theorem-proving prototypes. by Hairuo Guo. M.Eng. M.Eng. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 38 pages eng Massachusetts Institute of Technology MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582 Electrical Engineering and Computer Science. Steps towards proof construction using reinforcement learning : environments and models for hypothesis-posing as subtask creation Thesis application/pdf 2020-03-24T15:36:06Z Publication Master EECS unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="0eaae686-0da2-4285-83a5-ef9d98347463"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Language>eng</Language> <Title>Steps towards proof construction using reinforcement learning : environments and models for hypothesis-posing as subtask creation</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2019</PublicationDate> <Authors> <Author> <DisplayName>Guo, Hairuo.</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>http://dspace.mit.edu/handle/1721.1/7582</License> <Keyword>Electrical Engineering and Computer Science.</Keyword> <Abstract>Despite recent advances in reinforcement learning (RL) that have allowed AI algorithms to master games such as Go from scratch, scant progress has been made on applying RL to one of the first tasks seen as susceptible to automation: theorem proving. I present steps towards training agents to construct proofs through utilizing the ability to pose hypotheses as a way to uncover information and break tasks down into subtasks. To do so, I create a novel bitstring problem that retains many of the challenges posed by proof construction while dispensing with the need to parse grammars. I then assess the performance of well-known RL algorithms on tasks derived from this problem, demonstrating that it is non-trivial. Finally, I alter a model that successfully learns one of the bitstring tasks in order to acquire results on possible mechanisms for theorem-proving prototypes.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>