Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Robot Learning From Demonstration
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Learning CPG-based Biped Locomotion with a Policy Gradient Method: Application to a Humanoid Robot
International Journal of Robotics Research
Infinite-horizon policy-gradient estimation
Journal of Artificial Intelligence Research
Learning and generalization of motor skills by learning from demonstration
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations
IEEE Transactions on Robotics
On Learning, Representing, and Generalizing a Task in a Humanoid Robot
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A robot learning from demonstration framework to perform force-based manipulation tasks
Intelligent Service Robotics
Reinforcement learning in robotics: A survey
International Journal of Robotics Research
Interaction learning for dynamic movement primitives used in cooperative robotic tasks
Robotics and Autonomous Systems
Hi-index | 0.00 |
When describing robot motion with dynamic movement primitives (DMPs), goal (trajectory endpoint), shape and temporal scaling parameters are used. In reinforcement learning with DMPs, usually goals and temporal scaling parameters are predefined and only the weights for shaping a DMP are learned. Many tasks, however, exist where the best goal position is not a priori known, requiring to learn it. Thus, here we specifically address the question of how to simultaneously combine goal and shape parameter learning. This is a difficult problem because learning of both parameters could easily interfere in a destructive way. We apply value function approximation techniques for goal learning and direct policy search methods for shape learning. Specifically, we use ''policy improvement with path integrals'' and ''natural actor critic'' for the policy search. We solve a learning-to-pour-liquid task in simulations as well as using a Pa10 robot arm. Results for learning from scratch, learning initialized by human demonstration, as well as for modifying the tool for the learned DMPs are presented. We observe that the combination of goal and shape learning is stable and robust within large parameter regimes. Learning converges quickly even in the presence of disturbances, which makes this combined method suitable for robotic applications.