Model-based and model-free reinforcement learning for visual servoing

Amir Massoud Farahmand, Azad Shademan, Martin Jägersand, Csaba SzepesváriICRA 2009 · OpenReview

Abstract

To address the difficulty of designing a controller for complex visual-servoing tasks, two learning-based uncalibrated approaches are introduced. The first method starts by building an estimated model for the visual-motor forward kinematic of the vision-robot system by a locally linear regression method. Afterwards, it uses a reinforcement learning method named Regularized Fitted Q-Iteration to find a controller (i.e. policy) for the system (model-based RL). The second method directly uses samples coming from the robot without building any intermediate model (model-free RL). The simulation results show that both methods perform comparably well despite not having any a priori knowledge about the robot.
BibTeX
@inproceedings{farahmand2009model,
  author = {Amir Massoud Farahmand and Azad Shademan and Martin Jägersand and Csaba Szepesvári},
  title = {{Model-based and model-free reinforcement learning for visual servoing}},
  booktitle = {IEEE International Conference on Robotics and Automation},
  year = {2009},
  url = {https://openreview.net/forum?id=NssleRPyK4c},
}

Loading related content...

Figure