Hirotaka Hachiya

Alumni

Empirical Inference

Publications

5 results (View BibTeX file of all listed publications)

2011

Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning

Hachiya, H., Peters, J., Sugiyama, M.

Neural Computation, 23(11):2798-2832, November 2011 (article)

Abstract

Direct policy search is a promising reinforcement learning framework, in particular for controlling continuous, high-dimensional systems. Policy search often requires a large number of samples for obtaining a stable policy update estimator, and this is prohibitive when the sampling cost is expensive. In this letter, we extend an expectation-maximization-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, reward-weighted regression with sample reuse (R), is demonstrated through robot learning experiments.

Web DOI [BibTex]

2011

Hachiya, H., Peters, J., Sugiyama, M. Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning Neural Computation, 23(11):2798-2832, November 2011 (article)

Web DOI [BibTex]

2009

Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.

Neural Networks, 22(10):1399-1410, December 2009 (article)

Abstract

Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.

PDF Web DOI [BibTex]

2009

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J. Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning Neural Networks, 22(10):1399-1410, December 2009 (article)

PDF Web DOI [BibTex]

Efficient Sample Reuse in EM-Based Policy Search

Hachiya, H., Peters, J., Sugiyama, M.

In 16th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pages: 469-484, (Editors: Buntine, W. , M. Grobelnik, D. Mladenic, J. Shawe-Taylor), Springer, Berlin, Germany, ECML PKDD, September 2009 (inproceedings)

Abstract

Direct policy search is a promising reinforcement learning framework in particular for controlling in continuous, high-dimensional systems such as anthropomorphic robots. Policy search often requires a large number of samples for obtaining a stable policy update estimator due to its high flexibility. However, this is prohibitive when the sampling cost is expensive. In this paper, we extend a EM-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, called Reward-weighted Regression with sample Reuse, is demonstrated through a robot learning experiment.

PDF Web DOI [BibTex]

Hachiya, H., Peters, J., Sugiyama, M. Efficient Sample Reuse in EM-Based Policy Search In 16th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pages: 469-484, (Editors: Buntine, W. , M. Grobelnik, D. Mladenic, J. Shawe-Taylor), Springer, Berlin, Germany, ECML PKDD, September 2009 (inproceedings)

PDF Web DOI [BibTex]

Efficient data reuse in value function approximation

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.

In IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pages: 8-15, IEEE Service Center, Piscataway, NJ, USA, IEEE ADPRL, May 2009 (inproceedings)

Abstract

Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. The usefulness of the proposed approach is demonstrated through simulated swing-up inverted-pendulum problem.

PDF Web DOI [BibTex]

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J. Efficient data reuse in value function approximation In IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning, pages: 8-15, IEEE Service Center, Piscataway, NJ, USA, IEEE ADPRL, May 2009 (inproceedings)

PDF Web DOI [BibTex]

2008

Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.

In AAAI 2008, pages: 1351-1356, (Editors: Fox, D. , C. P. Gomes), AAAI Press, Menlo Park, CA, USA, Twenty-Third Conference on Artificial Intelligence, July 2008 (inproceedings)

Abstract

Off-policy reinforcement learning is aimed at efficiently reusing data samples gathered in the past, which is an essential problem for physically grounded AI as experiments are usually prohibitively expensive. A common approach is to use importance sampling techniques for compensating for the bias caused by the difference between data-sampling policies and the target policy. However, existing off-policy methods do not often take the variance of value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.

PDF Web [BibTex]

2008

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J. Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation In AAAI 2008, pages: 1351-1356, (Editors: Fox, D. , C. P. Gomes), AAAI Press, Menlo Park, CA, USA, Twenty-Third Conference on Artificial Intelligence, July 2008 (inproceedings)

PDF Web [BibTex]