20.500.12556/DiRROS-20517 Transfer learning in robotics An upcoming breakthrough? A review of promises and challenges Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied agents. The core concept— reusing prior knowledge to learn in and from novel situations—is successfully leveraged by humans to handle novel situations. In recent years, transfer learning has received renewed interest from the community from different perspectives, including imitation learning, domain adaptation, and transfer of experience from simulation to the real world, among others. In this paper, we unify the concept of transfer learning in robotics and provide the first taxonomy of its kind considering the key concepts of robot, task, and environment. Through a review of the promises and challenges in the field, we identify the need of transferring at different abstraction levels, the need of quantifying the transfer gap and the quality of transfer, as well as the dangers of negative transfer. Via this position paper, we hope to channel the effort of the community towards the most significant roadblocks to realize the full potential of transfer learning in robotics robotika strojno učenje true false true SAGE Publications ZDA Angleški jezik Slovenski jezik © The Author(s) 2024. Neznano 2024-10-07 11:08:08 2024-10-07 11:08:08 2024-10-08 03:35:23 0000-00-00 00:00:00 2024 0 0 21 str. [in press] 2024 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2023-11-29 2024-07-04 2024-09-13 007.5 0278-3649 10.1177/02783649241273565 208015875 RAZ_Jaquier_Noemie_2024.pdf RAZ_Jaquier_Noemie_2024.pdf 1 484BBC7BF4B76AE45B49CD69CC40F2A1 2ed7cb94174645fd1b8c8293bfe68f52bc934033b5c36a11e6e789ad028acd78 acd7777b-848c-11ef-a5bf-001a4af901a5 https://dirros.openscience.si/Dokument.php?lang=slv&id=28925 Institut Jožef Stefan 0 0 0