Abstract
Personalised robots have immense potential to enhance daily life through tailored interactions, yet achieving efficient personalisation remains challenging. This paper introduces a Multi-task Interactive Reinforcement Learning (MIRL) framework aimed at improving the efficiency of interactive learning with evaluative feedback. We demonstrate that pre-training the robot across diverse tasks significantly reduces the learning steps required during fine-tuning, thereby enhancing sample efficiency. Our approach effectively aligns robot behaviours with user preferences, as evidenced by experimental results. These advancements promise to advance the usability and effectiveness of personalised robotics in diverse applications.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdulhai, M., Jaques, N., Levine, S.: Basis for intentions: efficient inverse reinforcement learning using past experience. arXiv preprint arXiv:2208.04919 (2022)
Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469–483 (2009)
Chetouani, M.: Interactive robot learning: an overview. ECCAI Advanced Course on Artificial Intelligence, pp. 140–172 (2021)
Chevalier-Boisvert, M., et al.: BabyAI: a platform to study the sample efficiency of grounded language learning. arXiv preprint arXiv:1810.08272 (2018)
Churamani, N., et al.: The impact of personalisation on human-robot interaction in learning scenarios. In: Proceedings of the 5th International Conference on Human Agent Interaction, pp. 171–180 (2017)
Conti, D., Trubia, G., Buono, S., Di Nuovo, S., Di Nuovo, A.: An empirical study on integrating a small humanoid robot to support the therapy of children with autism spectrum disorder and intellectual disability. Interact. Stud. 22(2), 177–211 (2021)
Hejna III, D.J., Sadigh, D.: Few-shot preference learning for human-in-the-loop RL. In: Conference on Robot Learning, pp. 2014–2025. PMLR (2023)
Knox, W.B., Stone, P.: Framing reinforcement learning from human reward: reward positivity, temporal discounting, episodicity, and performance. Artif. Intell. 225, 24–50 (2015)
Li, G., He, B., Gomez, R., Nakamura, K.: Interactive reinforcement learning from demonstration and human evaluative feedback. In: 2018 27th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 1156–1162. IEEE (2018)
Moniruzzaman, M., Rassau, A., Chai, D., Islam, S.M.S.: Teleoperation methods and enhancement techniques for mobile robots: a comprehensive survey. Robot. Auton. Syst. 150, 103973 (2022)
Najar, A., Chetouani, M.: Reinforcement learning with human advice: a survey. Front. Rob. AI 8, 584075 (2021)
Stolarz, M., Mitrevski, A., Wasil, M., Plöger, P.G.: Learning-based personalisation of robot behaviour for robot-assisted therapy. Front Rob. AI 11, 1352152 (2024)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT press (2018)
Taiga, A.A., Agarwal, R., Farebrother, J., Courville, A., Bellemare, M.G.: Investigating multi-task pretraining and generalization in reinforcement learning. In: The Eleventh International Conference on Learning Representations (2023)
Tarakli, I., et al.: Social robots personalisation: at the crossroads between engineering and humanities (concatenate). In: Companion of the 2023 ACM/IEEE International Conference on Human-Robot Interaction, pp. 920–922 (2023)
Thomaz, A.L., Breazeal, C., et al.: Reinforcement learning with human teachers: evidence of feedback and guidance with implications for learning performance. In: AAAI, vol. 6, pp. 1000–1005. Boston, MA (2006)
Vagnetti, R., et al.: Robot companions and sensors for better living: defining needs to empower low socio-economic older adults at home. In: International Conference on Social Robotics, pp. 373–383. Springer (2023)
Acknowledgement
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 955778. For the purpose of open access, the author has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising from this submission.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Tarakli, I., Di Nuovo, A. (2025). Personalised Interactive Reinforcement Learning with Multi-task Pre-training. In: Paolillo, A., Giusti, A., Abbate, G. (eds) Human-Friendly Robotics 2024. HFR 2024. Springer Proceedings in Advanced Robotics, vol 35. Springer, Cham. https://doi.org/10.1007/978-3-031-81688-8_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-81688-8_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-81687-1
Online ISBN: 978-3-031-81688-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)