Abstract
We present a novel Bayesian reinforcement learning algorithm that addresses model bias and exploration overhead issues. The algorithm combines different aspects of several state-of-the-art reinforcement learning methods that use Gaussian Processes model-based approaches to increase the use of the online data samples. The algorithm uses a smooth reward function requiring the reward value to be derived from the environment state. It works with continuous states and actions in a coherent way with a minimized need for expert knowledge in parameter tuning. We analyse and discuss the practical benefits of the selected approach in comparison to more traditional methodological choices, and illustrate the use of the algorithm in a motor control problem involving a two-link simulated arm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Abbeel, P., Coates, A., Quigley, M., Ng, A.: An application of reinforcement learning to aerobatic helicopter flight. In: Advances in Neural Information Processing Systems, vol. 19, pp. 1–8 (2007)
Głowacka, D., Ruotsalo, T., Konuyshkova, K., Kaski, S., Jacucci, G.: Directing exploratory search: Reinforcement learning from user interactions with keywords. In: Proceedings of the 2013 International Conference on Intelligent User Interfaces, pp. 117–128. ACM (2013)
Kober, J., Peters, J.: Reinforcement learning in robotics: A survey. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning. ALO, vol. 12, pp. 569–600. Springer, Heidelberg (2012)
Arleo, A., Smeraldi, F., Gerstner, W.: Cognitive navigation based on nonuniform gabor space sampling, unsupervised growing networks, and reinforcement learning. IEEE Transactions on Neural Networks 15(3), 639–652 (2004)
Montazeri, H., Moradi, S., Safabakhsh, R.: Continuous state/action reinforcement learning: A growing self-organizing map approach. Neurocomputing 74(7), 1069–1082 (2011)
Graziano, V., Koutník, J., Schmidhuber, J.: Unsupervised modeling of partially observable environments. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011, Part I. LNCS (LNAI), vol. 6911, pp. 503–515. Springer, Heidelberg (2011)
Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction. Cambridge Univ. Press (1998)
Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical report, Cambridge University Engineering Dept. (1994)
Deisenroth, M.P., Rasmussen, C.E.: PILCO: A model-based and data-efficient approach to policy search. In: Proceedings of the International Conference on Machine Learning (2011)
Deisenroth, M.P., Rasmussen, C.E.: Efficient reinforcement learning for motor control. In: Proceedings of the 10th International PhD Workshop on Systems and Control, Hlubok nad Vltavou, Czech Republic (2009)
Körding, K.P., Wolpert, D.M.: The loss function of sensorimotor learning. Proceedings of the National Academy of Sciences of the United States of America 101(26), 9839–9842 (2004)
Rasmussen, C.E., Kuss, M.: Gaussian processes in reinforcement learning. In: Advances in Neural Information Processing Systems 16, pp. 751–759. MIT Press (2004)
Jakab, H., Csató, L.: Improving Gaussian process value function approximation in policy gradient algorithms. In: Honkela, T. (ed.) ICANN 2011, Part II. LNCS, vol. 6792, pp. 221–228. Springer, Heidelberg (2011)
Englert, P., Paraschos, A., Peters, J., Deisenroth, M.P.: Model-based imitation learning by probabilistic trajectory matching. In: Proceedings of 2013 IEEE International Conference on Robotics and Automation (ICRA) (2013)
Ko, J., Klein, D.J.: Gaussian processes and reinforcement learning for identification and control of an autonomous blimp. In: IEEE Intl. Conf. on Robotics and Automation (ICRA) (2007)
Ghavamzadeh, M., Engel, Y.: Bayesian actor-critic algorithms. In: Proceedings of the 24th International Conference on Machine Learning, ICML 2007, pp. 297–304. ACM, New York (2007)
Sugiyama, M., Hachiya, H., Towell, C., Vijayakumar, S.: Geodesic Gaussian kernels for value function approximation. Auton. Robots 25(3), 287–304 (2008)
Engel, Y., Mannor, S., Meir, R.: Reinforcement learning with Gaussian processes. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 201–208. ACM, New York (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Strahl, J., Honkela, T., Wagner, P. (2014). A Gaussian Process Reinforcement Learning Algorithm with Adaptability and Minimal Tuning Requirements. In: Wermter, S., et al. Artificial Neural Networks and Machine Learning – ICANN 2014. ICANN 2014. Lecture Notes in Computer Science, vol 8681. Springer, Cham. https://doi.org/10.1007/978-3-319-11179-7_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-11179-7_47
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11178-0
Online ISBN: 978-3-319-11179-7
eBook Packages: Computer ScienceComputer Science (R0)