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 | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
Control
| Record Number | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
Learning Motor Primitives
| Record Number | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
Robotics
| Record Number | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
Human Motor Control
| Record Number | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
Book Reviews
| Record Number | 2574 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J.;Vijayakumar, S.;Schaal, S. |
| Year | 2005 |
| Title | Natural Actor-Critic |
| Journal/Conference/Book Title | Proceedings of the 16th European Conference on Machine Learning (ECML 2005) |
| Keywords | Reinforcement Learning, Policy Gradients, Natural Gradients |
| Abstract | This paper investigates a novel model-free reinforcement learning architecture, the Natural Actor-Critic. The actor updates are based on stochastic policy gradients employing AmariÕs natural gradient approach, while the critic obtains both the natural policy gradient and additional parameters of a value function simultaneously by linear regres- sion. We show that actor improvements with natural policy gradients are particularly appealing as these are independent of coordinate frame of the chosen policy representation, and can be estimated more efficiently than regular policy gradients. The critic makes use of a special basis function parameterization motivated by the policy-gradient compatible function approximation. We show that several well-known reinforcement learning methods such as the original Actor-Critic and BradtkeÕs Linear Quadratic Q-Learning are in fact Natural Actor-Critic algorithms. Em- pirical evaluations illustrate the effectiveness of our techniques in com- parison to previous methods, and also demonstrate their applicability for learning control on an anthropomorphic robot arm. |
| Notes | clmc |
| Editor(s) | Gama, J.;Camacho, R.;Brazdil, P.;Jorge, A.;Torgo, L. |
| Place Published | Porto, Portugal, Oct. 3-7 |
| Publisher | Springer |
| Volume | 3720 |
| Pages | 280-291 |
| Tertiary Title | Lecture Notes in Computer Science |
| Short Title | Natural Actor-Critic |
| URL(s) | http://www-clmc.usc.edu/publications/P/peters-ECML2005.pdf |
The majority of the publications can also be obtained by Google Scholar where incomplete lists of citations are also given.