Sciweavers

2108 search results - page 23 / 422
» Tracking in Reinforcement Learning
Sort
View
ICMLA
2003
13 years 8 months ago
Reinforcement Learning Task Clustering
This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks th...
James L. Carroll, Todd S. Peterson, Kevin D. Seppi
NIPS
1992
13 years 8 months ago
Using Aperiodic Reinforcement for Directed Self-Organization During Development
We present a local learning rule in which Hebbian learning is conditional on an incorrect prediction of a reinforcement signal. We propose a biological interpretation of such a fr...
P. Read Montague, Peter Dayan, Steven J. Nowlan, T...
ACMSE
2010
ACM
13 years 5 months ago
Generating three binary addition algorithms using reinforcement programming
Reinforcement Programming (RP) is a new technique for automatically generating a computer program using reinforcement learning methods. This paper describes how RP learned to gene...
Spencer K. White, Tony R. Martinez, George L. Rudo...
ECAL
2007
Springer
13 years 11 months ago
Genotype Reuse More Important than Genotype Size in Evolvability of Embodied Neural Networks
odel of Embodiment on Abstract Systems: from Hierarchy to Heterarchy Kohei Nakajima, Soya Shinkai, Takashi Ikegami A Behavior-Based Model of the Hydra, Phylum Cnidaria Malin Aktius...
Chad W. Seys, Randall D. Beer
ATAL
2004
Springer
14 years 24 days ago
From Global Selective Perception to Local Selective Perception
This paper presents a reinforcement learning algorithm used to allocate tasks to agents in an uncertain real-time environment. In such environment, tasks have to be analyzed and a...
Sébastien Paquet, Nicolas Bernier, Brahim C...