Abstract
A long term goal in robotics is lifelong learning, in which a robot learns to perform new tasks without human intervention. For this a promising alternative is reinforcement learning (RL), in which an agent learns how to solve sequential decision-making problems by interacting with its environment. Despite the effectiveness of RL, learning in a trial-and-error way can be infeasible in robotics applications, in which long training periods can significantly deteriorate hardware. For robots that face long sequences of tasks, transfer learning represents an alternative to reduce training time, by transferring knowledge from previously learned tasks. However, in domains such as service robotics, identifying reusable pieces of knowledge and transferring them across tasks can be challenging, due to the mismatch between the state-action spaces (heterogeneous tasks). Thus, in this article we present an inter-task similarity measure and a transfer learning method for heterogeneous tasks. Through experimental evaluations, we show that the proposed measure is able to rank tasks in a way that prioritizes those that cause a larger increment of the learning performance in a target task. Additionally, results show that for some tasks the similarity measure can be computed with few data, enabling significant speedups in the learning process by transferring knowledge at an early stage.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ammar, H.B., et al.: An automated measure of MDP similarity for transfer in reinforcement learning. In: Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)
Bellman, R.E.: Dynamic programming (1957)
Brockman, G., et al.: Openai gym (2016)
Carroll, J.L., Seppi, K.: Task similarity measures for transfer in reinforcement learning task libraries. In: Proceedings of the 2005 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 803–808. IEEE (2005)
Ferns, N., Panangaden, P., Precup, D.: Metrics for finite Markov decision processes. In: UAI, vol. 4, pp. 162–169 (2004)
Ferns, N., Panangaden, P., Precup, D.: Metrics for Markov decision processes with infinite state spaces. arXiv preprint arXiv:1207.1386 (2012)
Henrikson, J.: Completeness and total boundedness of the Hausdorff metric. MIT Undergraduate J. Math. 1, 69–80 (1999)
Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238–1274 (2013)
Lin, K., Wang, S., Zhou, J.: Collaborative deep reinforcement learning. arXiv preprint arXiv:1702.05796 (2017)
Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley, Hoboken (2014)
Song, J., Gao, Y., Wang, H., An, B.: Measuring the distance between finite Markov decision processes. In: Proceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems, pp. 468–476 (2016)
Sorg, J., Singh, S.: Transfer via soft homomorphisms. In: Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems, vol. 2, pp. 741–748 (2009)
Taylor, M.E., Kuhlmann, G., Stone, P.: Autonomous transfer for reinforcement learning. In: AAMAS (1), pp. 283–290. Citeseer (2008)
Taylor, M.E., Stone, P.: Representation transfer for reinforcement learning. In: AAAI Fall Symposium: Computational Approaches to Representation Change during Learning and Development, pp. 78–85 (2007)
Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10(Jul), 1633–1685 (2009)
Wan, M., Gangwani, T., Peng, J.: Mutual information based knowledge transfer under state-action dimension mismatch. arXiv preprint arXiv:2006.07041 (2020)
Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Serrano, S.A., Martinez-Carranza, J., Sucar, L.E. (2022). Inter-task Similarity Measure for Heterogeneous Tasks. In: Alami, R., Biswas, J., Cakmak, M., Obst, O. (eds) RoboCup 2021: Robot World Cup XXIV. RoboCup 2021. Lecture Notes in Computer Science(), vol 13132. Springer, Cham. https://doi.org/10.1007/978-3-030-98682-7_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-98682-7_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98681-0
Online ISBN: 978-3-030-98682-7
eBook Packages: Computer ScienceComputer Science (R0)