Reinforcement Learning for Robotic Reaching and Grasping

  title={Reinforcement Learning for Robotic Reaching and Grasping},
  author={Andrew H. Fagg},
A reinforcement learning approach is used to train a neural controller to perform a robotic reaching task. Unlike supervised learning techniques, where the teacher must provide the correct sequence of motor actions, only an evaluation of the robot's performance is provided. From this limited information, the robot must discover the appropriate motor programs that best satisfy the teacher's evaluation criterion. This type of learning approach is important because in a real-world environment, the… CONTINUE READING
27 Citations
17 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 17 references

Real-Time Learning and Control using Asynchronous Dynamic Programming

  • A. G. Barto, S. H. Bradtke
  • TR 91-57,
  • 1991
2 Excerpts

A Menu of Designs for Reinforcement Learning Over Time, in Neural Networks for Control

  • P. J. Werbos
  • 1990
1 Excerpt

Connectionist Robot Motion Planning: A Neurally-Inspired Approach to Visually-Guided Reaching

  • B. W. Mel
  • Perspectives in Artificial Intelligence, B…
  • 1990
2 Excerpts

First Results with Dyna, An Integrated Architecture for Learning, Planning and Reacting, in Neural Networks for Control

  • R. S. Sutton
  • 1990
1 Excerpt

Similar Papers

Loading similar papers…