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 | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
Control
| Record Number | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
Learning Motor Primitives
| Record Number | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
Robotics
| Record Number | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
Human Motor Control
| Record Number | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
Book Reviews
| Record Number | 10174 |
| Reference Type | Conference Proceedings |
| Author(s) | Peters, J., Schaal, S. |
| Year | 2004 |
| Title | Learning Motor Primitives with Reinforcement Learning |
| Journal/Conference/Book Title | Proceedings of the 11th Joint Symposium on Neural Computation |
| Keywords | natural policy gradients, motor primitives, natural actor-critic |
| Abstract | One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion |
| Notes | clmc |
| Place Published | http://resolver.caltech.edu/CaltechJSNC:2004.poster020 |
The majority of the publications can also be obtained by Google Scholar where incomplete lists of citations are also given.