17 search results - page 1 / 4 » Reduction of Learning Time for Robots Using Automatic State ... |
EUROS
2006
13 years 9 months ago
2006
RSS
2007
13 years 6 months ago
2007
Abstract— This paper considers the problem of learning to recognize different terrains from color imagery in a fully automatic fashion, using the robot’s mechanical sensors as ...
ICML
1999
IEEE
14 years 6 months ago
1999
IEEE
ing from Robot Sensor Data using Hidden Markov Models Laura Firoiu, Paul Cohen Computer Science Department, LGRC University of Massachusetts at Amherst, Box 34610 Amherst, MA 01003...
FLAIRS
2004
13 years 6 months ago
2004
er provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, ...
ATAL
2010
Springer
13 years 6 months ago
2010
Springer
This paper describes an algorithm, called CQ-learning, which learns to adapt the state representation for multi-agent systems in order to coordinate with other agents. We propose ...