Share This Author
Reinforcement learning in robotics: A survey
This article attempts to strengthen the links between the two research communities by providing a survey of work in reinforcement learning for behavior generation in robots by highlighting both key challenges in robot reinforcement learning as well as notable successes.
Policy search for motor primitives in robotics
A novel EM-inspired algorithm for policy learning that is particularly well-suited for dynamical system motor primitives is introduced and applied in the context of motor learning and can learn a complex Ball-in-a-Cup task on a real Barrett WAM™ robot arm.
Relative Entropy Inverse Reinforcement Learning
This paper proposes a model-free IRL algorithm, where the relative entropy between the empirical distribution of the state-action trajectories under a baseline policy and their distribution under the learned policy is minimized by stochastic gradient descent.
Learning to select and generalize striking movements in robot table tennis
- Katharina Muelling, J. Kober, Oliver Kroemer, Jan Peters
- Computer ScienceAAAI Fall Symposium: Robots Learning…
- 19 October 2012
This paper presents a new framework that allows a robot to learn cooperative table tennis from physical interaction with a human and shows that the resulting setup is capable of playing table tennis using an anthropomorphic robot arm.
Learning motor primitives for robotics
It is shown that two new motor skills, i.e., Ball-in-a-Cup and Ball-Paddling, can be learned on a real Barrett WAM robot arm at a pace similar to human learning while achieving a significantly more reliable final performance.
Reinforcement learning to adjust parametrized motor primitives to new situations
This paper proposes a method that learns to generalize parametrized motor plans by adapting a small set of global parameters, called meta-parameters, and introduces an appropriate reinforcement learning algorithm based on a kernelized version of the reward-weighted regression.
Reinforcement learning for control: Performance, stability, and deep approximators
Imitation and Reinforcement Learning
This article describes the dynamical system MPs representation in a way that it is straightforward to reproduce, and presents an appropriate imitation learning method, i.e., locally weighted regression, which can be used both for initializing RL tasks as well as for modifying the start-up phase in a rhythmic task.
Movement templates for learning of hitting and batting
- J. Kober, Katharina Muelling, Oliver Kroemer, Christoph H. Lampert, B. Schölkopf, Jan Peters
- Computer ScienceIEEE International Conference on Robotics and…
- 3 May 2010
The Ijspeert framework is reformulate to incorporate the possibility of specifying a desired hitting point and a desired hit velocity while maintaining all advantages of the original formulation and is shown to work well in two scenarios.
Reinforcement Learning to Adjust Robot Movements to New Situations
This paper describes how to learn such mappings from circumstances to meta-parameters using reinforcement learning, and uses a kernelized version of the reward-weighted regression to do so.