Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Compact Q-Learning for Micro-robots
 
conference paper

Compact Q-Learning for Micro-robots

Asadpour, M.  
•
Siegwart, R.  
2003
Proc. of the first European Conf. on Mobile Robots [ECMR]
1st European Conference on Mobile Robots (ECMR 2003)

Scaling down robots to miniature size introduces many new challenges including memory and program size limitations, low processor performance and low power autonomy. In this paper we describe the concept and implementation of learning of safe-wandering and light following tasks on the autonomous micro-robots, Alice. We propose a simplified reinforcement learning algorithm based on one step Q-learning that is optimized in speed and memory consumption. This algorithm uses only integer-based sum operators and avoids floating-point and multiplication operators.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

compactQlearning_for print version.pdf

Access type

openaccess

Size

261.01 KB

Format

Adobe PDF

Checksum (MD5)

93db5e550a7bbe633f9b94396c5c200d

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés