Sciweavers

527 search results - page 93 / 106
» Design beyond human abilities
Sort
View
AAAI
2006
13 years 10 months ago
Sample-Efficient Evolutionary Function Approximation for Reinforcement Learning
Reinforcement learning problems are commonly tackled with temporal difference methods, which attempt to estimate the agent's optimal value function. In most real-world proble...
Shimon Whiteson, Peter Stone
ECIS
2004
13 years 10 months ago
A conceptual framework of e-fraud control in an integrated supply chain
The integration of supply chains offers many benefits; yet, it may also render organisations more vulnerable to electronic fraud (e-fraud). E-fraud can drain on organisations'...
Lucian Vasiu
WSCG
2003
150views more  WSCG 2003»
13 years 10 months ago
Smart Objects for Attentive Agents
We present an extended framework for modelling agent-object interactions in virtual environments. Our framework is based on the concept of Smart Objects and provides agents with p...
Christopher Peters, Simon Dobbyn, Brian MacNamee, ...
GECCO
2008
Springer
179views Optimization» more  GECCO 2008»
13 years 9 months ago
Developing neural structure of two agents that play checkers using cartesian genetic programming
A developmental model of neural network is presented and evaluated in the game of Checkers. The network is developed using cartesian genetic programs (CGP) as genotypes. Two agent...
Gul Muhammad Khan, Julian Francis Miller, David M....
IJMMS
2000
104views more  IJMMS 2000»
13 years 8 months ago
World Wide Web navigation aid
The challenge for the World Wide Web user is to discover and rediscover useful information from very rich but also very diversified sources in the Web environment. The Web browser...
Milena M. Head, Norman P. Archer, Yufei Yuan