Open document
|
General information |
Author |
Janež, Tadej; Žabkar, Jure; Možina, Martin; Bratko, Ivan |
Published |
InTech Open Access Publisher, 2013
|
Edition |
|
Extend |
|
ISBN |
|
Abstract |
In this paper we explore the question: “Is it
possible to speed up the learning process of an
autonomous agent by performing experiments in a
more complex environment (i.e., an environment with
a greater number of different objects)?” To this end, we
use a simple robotic domain, where the robot has to
learn a qualitative model predicting the change in the
robot’s distance to an object. To quantify the
environment’s complexity, we defined cardinal
complexity as the number of objects in the robot’s
world, and behavioural complexity as the number of
objects’ distinct behaviours. We propose Error reduction
merging (ERM), a new learning method that
automatically discovers similarities in the structure of
the agent’s environment. ERM identifies different
types of objects solely from the data measured and
merges the observations of objects that behave in the
same or similar way in order to speed up the agent’s
learning. We performed a series of experiments in
worlds of increasing complexity. The results in our
simple domain indicate that ERM was capable of
discovering structural similarities in the data which
indeed made the learning faster, clearly superior to
conventional learning. This observed trend occurred
with various machine learning algorithms used inside
the ERM method. |
|
|
|
International Journal of Advanced Robotic Systems
Author: Ottaviano, Erika; Ceccarelli, Marco; Husty, Manfred; Yu, Sung-Hoon; Kim, Yong-Tae; Park, Chang-Woo; Hyun, Chang-Ho; Chen, Xiulong; Feng, Weiming; Sun, Xianyang; Gao, Qing; Grigorescu, Sorin M.; Pozna, Claudiu; Liu, Wanli; Zhankui, Wang; Guo, Meng; Fu, Guoyu; Zhang, Jin; Chen, Wenyuan; Peng, Fengchao; Yang, Pei; Chen, Chunlin; Ding, Rui; Yu, Junzhi; Yang, Qinghai; Tan, Min; Polden, Joseph; Pan, [...]
Published: 2004
|
|