Sciweavers

94 search results - page 3 / 19
» Piecemeal Learning of an Unknown Environment
Sort
View
ICRA
2000
IEEE
111views Robotics» more  ICRA 2000»
13 years 10 months ago
Learning Globally Consistent Maps by Relaxation
Mobile robots require the ability to build their own maps to operate in unknown environments. A fundamental problem is that odometry-based dead reckoning cannot be used to assign ...
Tom Duckett, Stephen Marsland, Jonathan Shapiro
MAGS
2010
81views more  MAGS 2010»
13 years 1 months ago
Task allocation learning in a multiagent environment: Application to the RoboCupRescue simulation
Coordinating agents in a complex environment is a hard problem, but it can become even harder when certain characteristics of the tasks, like the required number of agents, are un...
Sébastien Paquet, Brahim Chaib-draa, Patric...
IJAIT
2008
146views more  IJAIT 2008»
13 years 6 months ago
Learning to Behave in Space: a Qualitative Spatial Representation for Robot Navigation with Reinforcement Learning
ion mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving directio...
Lutz Frommberger
JMLR
2010
125views more  JMLR 2010»
13 years 1 months ago
Variational methods for Reinforcement Learning
We consider reinforcement learning as solving a Markov decision process with unknown transition distribution. Based on interaction with the environment, an estimate of the transit...
Thomas Furmston, David Barber
MCS
2007
Springer
14 years 11 days ago
An Ensemble Approach for Incremental Learning in Nonstationary Environments
Abstract. We describe an ensemble of classifiers based algorithm for incremental learning in nonstationary environments. In this formulation, we assume that the learner is presente...
Michael Muhlbaier, Robi Polikar