Abstract
This study proposes an approximate parametric model-based Bayesian reinforcement learning approach for robots, based on online Bayesian estimation and online planning for an estimated model. The proposed approach is designed to learn a robotic task with a few real-world samples and to be robust against model uncertainty, within feasible computational resources. The proposed approach employs two-stage modeling, which is composed of (1) a parametric differential equation model with a few parameters based on prior knowledge such as equations of motion, and (2) a parametric model that interpolates a finite number of transition probability models for online estimation and planning. The proposed approach modifies the online Bayesian estimation to be robust against approximation errors of the parametric model to a real plant. The policy planned for the interpolating model is proven to have a form of theoretical robustness. Numerical simulation and hardware experiments of a planar peg-in-hole task demonstrate the effectiveness of the proposed approach.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Asmuth, J., Li, L., Littman, M. L., Nouri, A., & Wingate, D. (2009). A Bayesian sampling approach to exploration in reinforcement learning. In Proceedings of conference on uncertainty in artificial intelligence (pp. 19–26). AUAI Press.
Atkeson, C. G., & Santamaria, J. C. (1997). A comparison of direct and model-based reinforcement learning. In Proceedings of international conference on robotics and automation (Vol. 4, pp. 3557–3564). IEEE.
Bertsekas, D. P., & Tsitsiklis, J. N. (1996). Neuro-dynamic programming. Belmont, MA: Athena Scientific.
Bishop, C. M. (2006). Pattern recognition and machine learning (information science and statistics). Secaucus, NJ: Springer.
Deisenroth, M., & Rasmussen, C. E. (2011). PILCO: A model-based and data-efficient approach to policy search. In Proceedings international conference on machine learning (pp. 465–472).
Duff, M. O. (2002). Optimal learning: Computational procedures for Bayes-adaptive Markov decision processes. Ph.D. thesis, University of Massachusetts Amherst.
Ghavamzadeh, M., Mannor, S., Pineau, J., & Tamar, A. (2015). Bayesian reinforcement learning: A survey. Foundations and Trends in Machine Learning, 8(5–6), 359–483.
Gopalan, A., & Mannor, S. (2015). Thompson sampling for learning parameterized Markov decision processes. In Conference on learning theory (pp. 861–898).
Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., et al. (2018). Soft actor-critic algorithms and applications. arXiv preprint. arXiv:1812.05905.
Kober, J., Bagnell, J. A., & Peters, J. (2013). Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32(11), 1238–1274.
Littman, M. L. (1994). Markov games as a framework for multi-agent reinforcement learning. In Machine learning proceedings 1994 (pp 157–163). Elsevier.
Mahmood, A. R., Korenkevych, D., Vasan, G., Ma, W., & Bergstra, J. (2018). Benchmarking reinforcement learning algorithms on real-world robots. In Conference on robot learning (pp. 561–591).
Mankowitz, D. J., Mann, T. A., Bacon, P. L., Precup, D., & Mannor, S. (2018). Learning robust options. In AAAI conference on artificial intelligence (pp. 6409–6416).
Morimoto, J., & Doya, K. (2005). Robust reinforcement learning. Neural Computation, 17(2), 335–359.
Nagabandi, A., Kahn, G., Fearing, R. S., & Levine, S. (2018). Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In Proceedings of international conference on robotics and automation (pp 7559–7566). IEEE.
Nilim, A., & El Ghaoui, L. (2005). Robust control of Markov decision processes with uncertain transition matrices. Operations Research, 53(5), 780–798.
Pinto, L., Davidson, J., Sukthankar, R., & Gupta, A. (2017). Robust adversarial reinforcement learning. In Proceedings of international conference on machine learning (pp. 2817–2826). JMLR. org.
Ross, S., Chaib-draa, B., & Pineau, J. (2008). Bayesian reinforcement learning in continuous POMDPs with application to robot navigation. In Proceedings of international conference on robotics and automation (pp 2845–2851).
Senda, K., & Tani, Y. (2014). Autonomous robust skill generation using reinforcement learning with plant variation. Advances in Mechanical Engineering, 6, 276264.
Smith, R. (2008). Open dynamics engine. http://www.ode.org/
Strens, M. (2000). A Bayesian framework for reinforcement learning. In Proceedings of international conference on machine learning (pp. 943–950).
Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning. An introduction. Cambridge, MA: MIT Press.
Sutton, R. S., Precup, D., & Singh, S. (1999). Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial Intelligence, 112(1–2), 181–211.
Zhou, K., & Doyle, J. C. (1998). Essentials of robust control (Vol. 104). Upper Saddle River, NJ: Prentice Hall.
Acknowledgements
A part of this work has been financially supported by a grant-in-aid for Scientific Research from the Ministry of Education, Science, Culture, and Sports of Japan.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Supplementary material 1 (mp4 5417 KB)
Rights and permissions
About this article
Cite this article
Senda, K., Hishinuma, T. & Tani, Y. Approximate Bayesian reinforcement learning based on estimation of plant. Auton Robot 44, 845–857 (2020). https://doi.org/10.1007/s10514-020-09901-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10514-020-09901-4