Cogprints

Speeding up Learning with Dynamic Environment Shaping in Evolutionary Robotics

Bredeche, Nicolas and Hugues, Louis (2005) Speeding up Learning with Dynamic Environment Shaping in Evolutionary Robotics. [Conference Poster]

Full text available as:

[img]
Preview
PDF
3049Kb

Abstract

Evolutionary Robotics is a promising approach to automatically build efficient controllers using stochastic optimization techniques. However, works in this area are often confronted to complex environments where even simple tasks cannot be achieved. In the scope of this paper, we propose an approach based on explicit problem decomposition and dynamic environment shaping to ease the learning task.

Item Type:Conference Poster
Keywords:evolutionary robotics, developmental robot, task decomposition, dynamic fitness
Subjects:Computer Science > Machine Learning
Computer Science > Robotics
ID Code:4989
Deposited By:Prince, Dr Christopher G.
Deposited On:23 Jul 2006
Last Modified:11 Mar 2011 08:56

Metadata

Repository Staff Only: item control page