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 | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
Control
| Record Number | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
Learning Motor Primitives
| Record Number | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
Robotics
| Record Number | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
Human Motor Control
| Record Number | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
Book Reviews
| Record Number | 2673 |
| Reference Type | Conference Paper |
| Author(s) | Peters, J.;Schaal, S. |
| Year | 2007 |
| Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| Journal/Conference/Book Title | Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN) |
| Keywords | reinforcement learning, policy gradient methods, motor primitives, natural actor-critic |
| Abstract | In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. |
| Notes | clmc |
| Place Published | Bruges, Belgium, April 25-27 |
| Short Title | Applying the episodic natural actor-critic architecture to motor primitive learning |
| URL(s) | http://www-clmc.usc.edu/publications//P/peters-ESANN2007.pdf |
The majority of the publications can also be obtained by Google Scholar where incomplete lists of citations are also given.