• Publications
  • Influence
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. Expand
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. Expand
Policy Search for Motor Primitives in Robotics
This paper extends previous work on policy learning from the immediate reward case to episodic reinforcement learning, resulting in a general, common framework also connected to policy gradient methods and yielding a novel algorithm for policy learning that is particularly well-suited for dynamic motor primitives. Expand
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. Expand
Learning motor primitives for robotics
  • J. Kober, Jan Peters
  • Computer Science
  • IEEE International Conference on Robotics and…
  • 12 May 2009
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. Expand
Learning to select and generalize striking movements in robot table tennis
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. Expand
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. Expand
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. Expand
Movement templates for learning of hitting and batting
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. Expand
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. Expand