Compact Q-Learning Optimized for Micro-robots with Processing and Memory Constraints
Open access
Date
2004-08-31Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
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 a safe-wandering task with 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. Finally, quality of learning is compared to a floating-point based algorithm. Show more
Permanent link
https://doi.org/10.3929/ethz-a-010002588Publication status
publishedExternal links
Journal / series
Robotics and Autonomous SystemsVolume
Pages / Article No.
Publisher
ElsevierEvent
Subject
Reinforcement learning; Q-learning; Micro-robotsOrganisational unit
03737 - Siegwart, Roland Y. / Siegwart, Roland Y.
Related publications and datasets
Is new version of: https://doi.org/10.3929/ethz-a-010090674
More
Show all metadata
ETH Bibliography
yes
Altmetrics