Discovering Portable Options through Automated Mapping
dc.contributor.author | Topin, Nicholay | |
dc.contributor.author | Haltmeyer, Nicholas | |
dc.contributor.author | Squire, Shawn | |
dc.contributor.author | Winder, John | |
dc.contributor.author | MacGlashan, James | |
dc.contributor.author | desJardins, Marie | |
dc.date.accessioned | 2023-10-12T18:24:29Z | |
dc.date.available | 2023-10-12T18:24:29Z | |
dc.description.abstract | Goal for artificial agents: Learn the most efficient process for completing a task in a given domain o Corollary: Reuse and transfer learned knowledge o Previous work assumed that a mapping was provided or that all domains were identical o Our contributions: Automatically map across domains with different objects and attributes Leverage prior knowledge by identifying commonalities between source and target domains Provide novel techniques for scoring mappings and abstracting domains o Our method outperforms Pickett and Barto's PolicyBlocks (2002) and MacGlashan's Transfer Options (2013) | en_US |
dc.description.sponsorship | This work was supported by NSF’s Division of Information and Intelligent Systems on awards #1065228 and #1340150 (REU supplement). We would like to thank the other coPIs on the project, Michael Littman and Smaranda Muresan, for many fruitful discussions. | en_US |
dc.description.uri | http://hpcf-files.umbc.edu/research/posters/DesJardins_HPCF_Poster.pdf | en_US |
dc.format.extent | 1 page | en_US |
dc.genre | posters | en_US |
dc.identifier | doi:10.13016/m2nyiv-xspp | |
dc.identifier.uri | http://hdl.handle.net/11603/30094 | |
dc.language.iso | en_US | en_US |
dc.relation.isAvailableAt | The University of Maryland, Baltimore County (UMBC) | |
dc.relation.ispartof | UMBC Computer Science and Electrical Engineering Department Collection | |
dc.relation.ispartof | UMBC Faculty Collection | |
dc.relation.ispartof | UMBC Student Collection | |
dc.relation.ispartof | UMBC College of Engineering and Information Technology Dean's Office | |
dc.rights | This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author. | en_US |
dc.title | Discovering Portable Options through Automated Mapping | en_US |
dc.type | Text | en_US |