Abstract
In this paper, we introduce a novel method for learning simultaneously a task and the related social interaction. We present an architecture based on Learning Classifier Systems that simultaneously learns a model of social interaction and uses it to bootstrap task learning, while minimizing the number of interactions with the human. We validate our method in simulation and we prove the feasibility of our approach on a real robot.
Preview
Unable to display preview. Download preview PDF.
References
Corrigan, L.J., Peters, C., Castellano, G., Papadopoulos, F., Jones, A., Bhargava, S., Janarthanam, S., Hastie, H., Deshmukh, A., Aylett, R.: Social-task engagement: striking a balance between the robot and the task. In: Embodied Commun. Goals Intentions Workshop ICSR, vol. 13, pp. 1–7 (2013)
Grizou, J., Lopes, M., Oudeyer, P.-Y.: Robot learning simultaneously a task and how to interpret human instructions. In: 2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL), pp. 1–8, August 2013
Isbell, C., Shelton, C.R., Kearns, M., Singh, S., Stone, P.: A social reinforcement learning agent. In: Proceedings of the Fifth International Conference on Autonomous Agents, pp. 377–384. ACM (2001)
Kim, E., Scassellati, B.: Learning to refine behavior using prosodic feedback. In: IEEE 6th International Conference on Development and Learning, ICDL 2007, pp. 205–210, July 2007
Knox, W.B., Stone, P.: Combining manual feedback with subsequent MDP reward signals for reinforcement learning. In: Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 2010
Najar, A., Sigaud, O., Chetouani, M.: Socially guided XCS: using teaching signals to boost learning. In: Proceedings of the Companion Publication of the 2015 on Genetic and Evolutionary Computation Conference, GECCO Companion 2015, pp. 1021–1028. ACM (2015)
Pilarski, P.M., Dawson, M.R., Degris, T., Fahimi, F., Carey, J.P., Sutton, R.S.: Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning. In: 2011 IEEE International Conference on Rehabilitation Robotics (ICORR), pp. 1–7. IEEE (2011)
Sigaud, O., Wilson, S.W.: Learning classifier systems: a survey. Soft Comput. 11(11), 1065–1078 (2007)
Suay, H.B., Chernova, S.: Effect of human guidance and state space size on interactive reinforcement learning. In: 2011 IEEE RO-MAN, pp. 1–6. IEEE (2011)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (1998)
Villaseñor-Pineda, L., Morales, E.F., Tenorio-Gonzalez, A.C.: Dynamic reward shaping: training a robot by voice. In: Kuri-Morales, A., Simari, G.R. (eds.) IBERAMIA 2010. LNCS, vol. 6433, pp. 483–492. Springer, Heidelberg (2010)
Thomaz, A.L., Breazeal, C.: Reinforcement learning with human teachers: evidence of feedback and guidance with implications for learning performance. In: AAAI, vol. 6, pp. 1000–1005 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Najar, A., Sigaud, O., Chetouani, M. (2015). Social-Task Learning for HRI. In: Tapus, A., André, E., Martin, JC., Ferland, F., Ammi, M. (eds) Social Robotics. ICSR 2015. Lecture Notes in Computer Science(), vol 9388. Springer, Cham. https://doi.org/10.1007/978-3-319-25554-5_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-25554-5_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25553-8
Online ISBN: 978-3-319-25554-5
eBook Packages: Computer ScienceComputer Science (R0)