Sciweavers

4263 search results - page 210 / 853
» Learning without Coding
Sort
View
IAT
2007
IEEE
15 years 8 months ago
Noise Tolerance in Reinforcement Learning Algorithms
This paper proposes a mechanism of noise tolerance for reinforcement learning algorithms. An adaptive agent that employs reinforcement learning algorithms may receive and accumula...
Richardson Ribeiro, Alessandro L. Koerich, Fabr&ia...
ROBOCUP
2005
Springer
99views Robotics» more  ROBOCUP 2005»
15 years 7 months ago
Keepaway Soccer: From Machine Learning Testbed to Benchmark
Keepaway soccer has been previously put forth as a testbed for machine learning. Although multiple researchers have used it successfully for machine learning experiments, doing so ...
Peter Stone, Gregory Kuhlmann, Matthew E. Taylor, ...
ICRA
1998
IEEE
144views Robotics» more  ICRA 1998»
15 years 6 months ago
Acquiring Mobile Robot Behaviors by Learning Trajectory Velocities with Multiple FAM Matrices
In this paper we describe an unsupervised robot learning method which is based on the robot learning a mapping between sensors and trajectory velocities. This enables the robot to...
Koren Ward, Alexander Zelinsky
FLAIRS
2008
15 years 4 months ago
One-Pass Learning Algorithm for Fast Recovery of Bayesian Network
An efficient framework is proposed for the fast recovery of Bayesian network classifier. A novel algorithm, called Iterative Parent-Child learningBayesian Network Classifier (IPC-...
Shunkai Fu, Michel Desmarais, Fan Li
NIPS
2007
15 years 3 months ago
Active Preference Learning with Discrete Choice Data
We propose an active learning algorithm that learns a continuous valuation model from discrete preferences. The algorithm automatically decides what items are best presented to an...
Eric Brochu, Nando de Freitas, Abhijeet Ghosh