Sciweavers

3274 search results - page 93 / 655
» Using Learning in a Control Agent
Sort
View
GECCO
2007
Springer
214views Optimization» more  GECCO 2007»
14 years 2 months ago
Portfolio allocation using XCS experts in technical analysis, market conditions and options market
Schulenburg [15] first proposed the idea to model different trader types by supplying different input information sets to a group of homogenous LCS agent. Gershoff [12] investigat...
Sor Ying (Byron) Wong, Sonia Schulenburg
PKDD
2000
Springer
108views Data Mining» more  PKDD 2000»
13 years 11 months ago
Application of Reinforcement Learning to Electrical Power System Closed-Loop Emergency Control
This paper investigates the use of reinforcement learning in electric power system emergency control. The approach consists of using numerical simulations together with on-policy M...
Christophe Druet, Damien Ernst, Louis Wehenkel
ICRA
2005
IEEE
159views Robotics» more  ICRA 2005»
14 years 1 months ago
Learning Sensory Feedback to CPG with Policy Gradient for Biped Locomotion
— This paper proposes a learning framework for a CPG-based biped locomotion controller using a policy gradient method. Our goal in this study is to develop an efficient learning...
Takamitsu Matsubara, Jun Morimoto, Jun Nakanishi, ...
DSVIS
2003
Springer
14 years 1 months ago
Improving User Interface Usability Using Mobile Agents
Adapting graphical user interface (GUI) to meet higher level of usability for users is one of the most interesting questions of today’s mobile computation. Users should have GUI ...
Nikola Mitrovic, Eduardo Mena
AIM
2006
13 years 8 months ago
The Pyro Toolkit for AI and Robotics
This article introduces Pyro, an open source python robotics toolkit for exploring topics in AI and robotics. nt key abstractions that allow Pyro controllers to run unchanged on a...
Douglas S. Blank, Deepak Kumar, Lisa Meeden, Holly...