{"type":"ScholarlyArticle","title":"GRAML: Goal Recognition As Metric Learning","authors":[{"name":"Matan Shamir","slug":"matan-shamir","given":"Matan","family":"Shamir","affiliation":""},{"name":"Reuth Mirsky","slug":"reuth-mirsky","given":"Reuth","family":"Mirsky","affiliation":""}],"abstract":"Goal Recognition (GR) is the problem of recognizing an agent's objectives based on observed actions. \r\nRecent data-driven approaches for GR alleviate the need for costly, manually crafted domain models. \r\nHowever, these approaches can only reason about a pre-defined set of goals, and time-consuming training is needed for new emerging goals. \r\nTo keep this model-learning automated while enabling quick adaptation to new goals, this paper introduces GRAML: Goal Recognition As Metric Learning. \r\nGRAML frames GR as a deep metric learning problem, using a Siamese network composed of recurrent units to learn an embedding space where traces leading to the same goal are close, and those leading to different goals are distant.\r\nThis metric is particularly effective for adapting to new goals, even when only a single example trace is available per goal.\r\nEvaluated on a versatile set of environments, GRAML shows speed, flexibility, and runtime improvements over the state-of-the-art GR while maintaining accurate recognition.","doi":"10.24963/ijcai.2025/959","url":"https://ijcai.org/proceedings/2025/959","pdf":"https://ijcai.org/proceedings/2025/0959.pdf","markdown":"https://ijcai.org/proceedings/2025/959.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/959","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Planning and Scheduling","track":"Main Track","number":959,"pages":{"first":8626,"last":8634},"keywords":["Agent-based and Multi-agent Systems: MAS: Agent theories and models","Planning and Scheduling: PS: Activity and plan recognition","Machine Learning: ML: Multiagent Reinforcement Learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}