{"type":"ScholarlyArticle","title":"Learning Portable Symbolic Representations","authors":[{"name":"Steven James","slug":"steven-james","given":"Steven","family":"James","affiliation":"School of Computer Science and Applied Mathematics University of the Witwatersrand , South Africa"}],"abstract":"An open question in artificial intelligence is how to learn useful representations of the real world. One approach is to learn symbols, which represent the world and its contents, as well as models describing the effects on these symbols when interacting with the world. To date, however, research has investigated learning such representations for a single specific task. Our research focuses on approaches to learning these models in a domain-independent manner. We intend to use these symbolic models to build even higher levels of abstraction, creating a hierarchical representation which could be used to solve complex tasks. This would allow an agent to gather knowledge over the course of its lifetime, which could then be leveraged when faced with a new task, obviating the need to relearn a model every time a new unseen problem is encountered.","doi":"10.24963/ijcai.2018/826","url":"https://ijcai.org/proceedings/2018/826","pdf":"https://ijcai.org/proceedings/2018/0826.pdf","markdown":"https://ijcai.org/proceedings/2018/826.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/826","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Doctoral Consortium","track":"Doctoral Consortium","number":826,"pages":{"first":5765,"last":5766},"keywords":["Machine Learning: Reinforcement Learning","Planning and Scheduling: Hierarchical planning","Machine Learning: Transfer, Adaptation, Multi-task Learning"],"videos":[],"references":[{"position":1,"raw":"[Diuk et al., 2008] Carlos Diuk, Andre Cohen, and Michael Littman. An object-oriented representation for efficient re- inforcement learning. In Proceedings of the 25th Interna- tional Conference on Machine learning, 2008.","title":"An object-oriented representation for efficient reinforcement learning","authors":"Carlos Diuk, Andre Cohen, Michael Littman","year":"2008","venue":"Proceedings of the 25th International Conference on Machine learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ghallab et al., 2004] Malik Ghallab, Dana Nau, and Paolo Traverso. Automated Planning: theory and practice. El- sevier, 2004.","title":"Automated Planning: theory and practice","authors":"Malik Ghallab, Dana Nau, Paolo Traverso","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Konidaris et al., 2012] George Konidaris, Ilya Scheid- wasser, and Andrew Barto. Transfer in reinforcement learning via shared features. Journal of Machine Learning Research, 13(May):1333-1371, 2012.","title":"Transfer in reinforcement learning via shared features","authors":"Konidaris","year":"2012","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Konidaris et al., 2018] George Konidaris, Leslie Pack Kael- bling, and Tomas Lozano-Pérez. From skills to sym- bols: Learning symbolic representations for abstract high- level planning. Journal of Artificial Intelligence Research, 61(January):215-289, 2018.","title":"George Konidaris, Leslie Pack Kaelbling, and Tomas Lozano-Pérez. From skills to symbols: Learning symbolic representations for abstract highlevel planning","authors":"Konidaris","year":"2018","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Konidaris, 2016] George Konidaris. Constructing abstrac- tion hierarchies using a skill-symbol loop. In Proceedings of the Twenty-Fifth International Joint Conference on Arti- ficial Intelligence, volume 2016, pages 1648-1654, 2016.","title":"Constructing abstraction hierarchies using a skill-symbol loop","authors":"George Konidaris","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/236"}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}