Abstract
Reinforcement learning agents can be helped by the knowledge transferred from experienced agents. This paper studies the problem of how an experienced agent helps another agent learn when they have different learning goals by action transfer. This problem is motivated by the widely existing situations where agents have different learning goals and only action transfer is available to agents. To tackle the problem, we propose an approach to facilitate the transfer of actions that are right to a learning agent’s goal. Experimental results show the effectiveness of the proposed approach in transferring right actions to an agent and helping the agent learn to reach a different goal.
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
Notes
- 1.
We follow a general setting where \( \pi \) is optimal. Considering sub-optimal \( \pi \) is not the main issue in this paper, and would be left as future work.
- 2.
There are multiple goals when multiple states have the same maximum V value. The technical details for multi-goal and one-goal situations are generally the same. We only describe the one-goal situation for clear description.
References
Amir, O., Kamar, E., Kolobov, A., Grosz, B.J.: Interactive teaching strategies for agent training. In: Proceedings of the 25th International Joint Conferences on Artificial Intelligence. pp. 804–811 (2016)
Chernova, S., Veloso, M.: Confidence-based policy learning from demonstration using gaussian mixture models. In: Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems. pp. 1315–1322 (2007)
Da Silva, F.L., Glatt, R., Costa, A.H.R.: Simultaneously learning and advising in multiagent reinforcement learning. In: Proceedings of the 16th Conference on Autonomous Agents and Multiagent Systems. pp. 1100–1108 (2017)
Fernández, F., Veloso, M.: Probabilistic policy reuse in a reinforcement learning agent. In: Proceedings of the fifth International Ioint Conference on Autonomous Agents and Multiagent Systems. pp. 720–727. ACM (2006)
Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons (2014)
Sherstov, A.A., Stone, P.: Improving action selection in mdp’s via knowledge transfer. In: Proceedings of the 20th National Conference on Artificial Intelligence. vol. 5, pp. 1024–1029 (2005)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. MIT Press (1998)
Taylor, M.E., Carboni, N., Fachantidis, A., Vlahavas, I., Torrey, L.: Reinforcement learning agents providing advice in complex video games. Connection Science 26(1), 45–63 (2014)
Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: A survey. Journal of Machine Learning Research 10, 1633–1685 (2009)
Torrey, L., Taylor, M.: Teaching on a budget: Agents advising agents in reinforcement learning. In: Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems. pp. 1053–1060 (2013)
Watkins, C.J., Dayan, P.: Q-learning. Machine Learning 8(3–4), 279–292 (1992)
Wilson, A., Fern, A., Ray, S., Tadepalli, P.: Multi-task reinforcement learning: a hierarchical bayesian approach. In: Proceedings of the 24th International Conference on Machine Learning. pp. 1015–1022. ACM (2007)
Ye, D., Zhu, T., Zhou, W., Philip, S.Y.: Differentially private malicious agent avoidance in multiagent advising learning. IEEE Transactions on Cybernetics (2019)
Yu, C., Zhang, M., Ren, F., Tan, G.: Multiagent learning of coordination in loosely coupled multiagent systems. IEEE Transactions on Cybernetics 45(12), 2853–2867 (2015)
Zhan, Y., Ammar, H.B., Taylor, M.E.: Theoretically-grounded policy advice from multiple teachers in reinforcement learning settings with applications to negative transfer. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence. pp. 2315–2321 (2016)
Acknowledgement
This research is supported by a DECRA Project (DP140100007) from Australia Research Council (ARC), a UPA and an IPTA scholarships from University of Wollongong, Australia.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, Y., Ren, F., Zhang, M. (2019). Helping an Agent Reach a Different Goal by Action Transfer in Reinforcement Learning. In: Liu, J., Bailey, J. (eds) AI 2019: Advances in Artificial Intelligence. AI 2019. Lecture Notes in Computer Science(), vol 11919. Springer, Cham. https://doi.org/10.1007/978-3-030-35288-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-35288-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35287-5
Online ISBN: 978-3-030-35288-2
eBook Packages: Computer ScienceComputer Science (R0)