Policy Search for Motor Primitives in Robotics

@inproceedings{Kober2008PolicySF,
  title={Policy Search for Motor Primitives in Robotics},
  author={J. Kober and Jan Peters},
  booktitle={NIPS 2008},
  year={2008}
}
Many motor skills in humanoid robotics can be learned using parametrized motor primitives as done in imitation learning. However, most interesting motor learning problems are high-dimensional reinforcement learning problems often beyond the reach of current methods. In this paper, we extend previous work on policy learning from the immediate reward case to episodic reinforcement learning. We show that this results in a general, common framework also connected to policy gradient methods and… Expand
Policy search for motor primitives in robotics
Learning motor primitives for robotics
  • J. Kober, Jan Peters
  • Computer Science
  • 2009 IEEE International Conference on Robotics and Automation
  • 2009
Learning New Basic Movements for Robotics
Reinforcement Learning to Adjust Robot Movements to New Situations
Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling
Reinforcement learning of full-body humanoid motor skills
Learning Replanning Policies With Direct Policy Search
Accounting for Task-Difficulty in Active Multi-Task Robot Control Learning
Robot Skill Acquisition by Demonstration and Explorative Learning
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 54 REFERENCES
Learning motor primitives for robotics
  • J. Kober, Jan Peters
  • Computer Science
  • 2009 IEEE International Conference on Robotics and Automation
  • 2009
Policy Gradient Methods for Robotics
  • Jan Peters, S. Schaal
  • Engineering, Computer Science
  • 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2006
Learning perceptual coupling for motor primitives
Reinforcement learning for imitating constrained reaching movements
Teaching by Showing in Kendama Based on Optimization Principle
Learning Attractor Landscapes for Learning Motor Primitives
Machine Learning for motor skills in robotics
Towards Direct Policy Search Reinforcement Learning for Robot Control
Reinforcement learning by reward-weighted regression for operational space control
...
1
2
3
4
5
...