ON LINE LEARNING: EVOLVING in REAL TIME a neural net Controller of 3D-robot-arm. Track and Evolve.

2006 ◽  
Author(s):  
A. Lehireche ◽  
A. Rahmoun
Keyword(s):  
Real Time ◽  
Neural Net ◽  
Robot Arm ◽  
On Line ◽  
On Line Learning

MODELING AND AUGMENTING GAME ENTERTAINMENT THROUGH CHALLENGE AND CURIOSITY

2007 ◽  
Vol 16 (06) ◽  
pp. 981-999 ◽  
Author(s):  
GEORGIOS N. YANNAKAKIS ◽  
JOHN HALLAM
Keyword(s):  
Real Time ◽  
Computer Games ◽  
Mixed Reality ◽  
Computer Game ◽  
Feedforward Neural Networks ◽  
Interactive Systems ◽  
Quantitative Measurements ◽  
Player Satisfaction ◽  
On Line ◽  
On Line Learning

This paper presents quantitative measurements/metrics of qualitative entertainment features within computer game environments and proposes artificial intelligence (AI) techniques for optimizing entertainment in such interactive systems. A human-verified metric of interest (i.e. player entertainment in real-time) for predator/prey games and a neuro-evolution on-line learning (i.e. during play) approach have already been reported in the literature to serve this purpose. In this paper, an alternative quantitative approach to entertainment modeling based on psychological studies in the field of computer games is introduced and a comparative study of the two approaches is presented. Feedforward neural networks (NNs) and fuzzy-NNs are used to model player satisfaction (interest) in real-time and investigate quantitatively how the qualitative factors of challenge and curiosity contribute to human entertainment. We demonstrate that appropriate non-extreme levels of challenge and curiosity generate high values of entertainment and we project the extensibility of the approach to other genres of digital entertainment (e.g. mixed-reality interactive playgrounds).

A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks

1992 ◽  
Vol 4 (2) ◽  
pp. 243-248 ◽  
Author(s):  
Jürgen Schmidhuber
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Learning Algorithm ◽  
Fixed Size ◽  
Time Step ◽  
The Real ◽  
On Line ◽  
On Line Learning

The real-time recurrent learning (RTRL) algorithm (Robinson and Fallside 1987; Williams and Zipser 1989) requires O(n4) computations per time step, where n is the number of noninput units. I describe a method suited for on-line learning that computes exactly the same gradient and requires fixed-size storage of the same order but has an average time complexity per time step of O(n3).

On-line learning of robot arm impedance using neural networks

2005 ◽  
Vol 52 (4) ◽  
pp. 257-271 ◽  
Author(s):  
Toshio Tsuji ◽  
Yoshiyuki Tanaka
Keyword(s):  
Neural Networks ◽  
Robot Arm ◽  
On Line ◽  
On Line Learning

Automated Modeling and Rapid Solution of Robot Dynamics Using the Symbolic Polynomial Technique

1987 ◽  
Author(s):  
M. A. Townsend ◽  
S. Gupta
Keyword(s):  
Real Time ◽  
Equations Of Motion ◽  
New Method ◽  
Dynamic Equations ◽  
Dynamic State ◽  
Robot Dynamics ◽  
Robot Arm ◽  
Numerical Computations ◽  
Automated Modeling ◽  
On Line

Abstract Fast and accurate solutions of the dynamic equations of a robot arm are required for real time on-line control. In this paper we present a new method for rapidly evaluating the exact dynamic state of a robot. This method uses a combination of symbolic and numerical computations on the equations of motion, which are developed in the form of polynomials — hence the name, the symbolic polynomial technique.

Sign in / Sign up

Export Citation Format

Share Document