Article

State Space Construction for Behavior Acquisition in Multi Agent Environments with Vision and Action

11/1998;
Source: CiteSeer

ABSTRACT This paper proposes a method which estimates the relationships between learner's behaviors and other agents' ones in the environment through interactions (observation and action) using the method of system identication. In order to identify the model of each agent, Akaike's Information Criterion is applied to the results of Canonical Variate Analysis for the relationship between the observed data in terms of action and future observation. Next, reinforcement learning based on the estimated state vectors is performed to obtain the optimal behavior. The proposed method is applied to a soccer playing situation, where a rolling ball and other moving agents are well modeled and the learner's behaviors are successfully acquired by the method. Computer simulations and real experiments are shown and a discussion is given. 1 Introduction Building a robot that learns to accomplish a task through visual information has been acknowledged as one of the major challenges facing vision, robotics, a...

0 0
 · 
0 Bookmarks
 · 
16 Views
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Full-text

View
0 Downloads
Available from

Keywords

agents' ones
 
Akaike's Information Criterion
 
Canonical Variate Analysis
 
estimated state vectors
 
future observation
 
learner's behaviors
 
learns
 
major challenges
 
moving agents
 
observed data
 
optimal behavior
 
proposed method
 
real experiments
 
reinforcement
 
relationships
 
rolling ball
 
system identication
 
visual information