Main » Publications by Topic
This list is automatically created, please see publications by year in order to have a more chronological overview on my publications. Note that the list on this page is automatically generated and as such always overlapping due to overlapping keywords.
Reinforcement Learning
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
Control
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
Learning Motor Primitives
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
Robotics
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
Human Motor Control
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
Book Reviews
| Record Number | 10198 |
| Reference Type | Journal Article |
| Author(s) | Hachiya,H.; Akiyama, T.; Sugiyama, M.; Peters, J. |
| Year | 2009 |
| Title | Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning |
| Journal/Conference/Book Title | Neural Networks |
| Keywords | off-policy reinforcement learning; value function approximation; policy iteration; adaptive importance sampling; importance-weighted cross-validation; efficient sample reuse |
| Abstract | Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a different policy than the currently optimized one. 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. |
| Notes | jan |
| Volume | 22 |
| Number | 10 |
| Pages | 1399-1410 |
The majority of the publications can also be obtained by Google Scholar where incomplete lists of citations are also given.