Abstract
Incorporating domain knowledge into conventional reinforcement learning has proven to be difficult due to its inability to fully extract the features of the demonstrator. We thus propose the use two algorithms for inverse reinforcement learning, Bayesian Neural Network and Maximum Entropy to deal with this issue. The primary objective of this work is to determine if varying qualities of domain knowledge, in the form of a demonstrator, would have any significant impact on the rewards obtained from the two algorithms by applying it to the mountain car environment.
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
Ramamurthy, R., Bauckhage, C., Sifa, R., Schücker, J., Wrobel, S.: Leveraging domain knowledge for reinforcement learning using MMC architectures. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11728, pp. 595–607. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30484-3_48
Oh, M., Iyengar, G.: Sequential Anomaly Detection using Inverse Reinforcement Learning. arXiv:2004.10398 (2020)
Wulfmeier, M., Ondruska, P., Posner, I.: Maximum entropy deep inverse reinforcement learning, arXiv:1507.04888 (2015)
Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. IEEE Int. Conf. Robot. Autom. (ICRA), 6292–6299(2018)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms. arXiv:1707.06347 (2017)
Sutton, R., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, MA (1998)
Russell, S.: Learning agents for uncertain environments. In: Proceedings of the Eleventh Annual Conference on Computational Learning Theory, ACM, 101– 103 (1998)
Abbeel, P., Andrew, N.: Apprenticeship learning via inverse reinforcement learning. In: Proceedings, Twenty-First International Conference on Machine Learning (2004). https://doi.org/10.1007/978-0-387-30164-8_417
Price, B., Boutilier, C.: A Bayesian Approach to Imitation in Reinforcement Learning, In: IJCAI 2003: Proceedings of the 18th International Joint Conference on Artificial Intelligence, pp. 712–717 (2003)
Ziebart, B.D., Maas, A., Bagnell, J.A., Dey, A.K.: Maximum entropy inverse reinforcement learning. In: Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, 1433–1438 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sogabe, R., Malla, D.B., Sogabe, M., Sakamoto, K., Sogabe, T. (2021). Impact of Domain Knowledge Quality on Inverse Reinforcement Learning. In: Yada, K., et al. Advances in Artificial Intelligence. JSAI 2020. Advances in Intelligent Systems and Computing, vol 1357. Springer, Cham. https://doi.org/10.1007/978-3-030-73113-7_9
Download citation
DOI: https://doi.org/10.1007/978-3-030-73113-7_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73112-0
Online ISBN: 978-3-030-73113-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)