Sciweavers

1233 search results - page 126 / 247
» Feudal Reinforcement Learning
Sort
View
ECAI
2006
Springer
13 years 11 months ago
Learning by Automatic Option Discovery from Conditionally Terminating Sequences
Abstract. This paper proposes a novel approach to discover options in the form of conditionally terminating sequences, and shows how they can be integrated into reinforcement learn...
Sertan Girgin, Faruk Polat, Reda Alhajj
GECCO
2006
Springer
208views Optimization» more  GECCO 2006»
13 years 11 months ago
Comparing evolutionary and temporal difference methods in a reinforcement learning domain
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
Matthew E. Taylor, Shimon Whiteson, Peter Stone
IAT
2008
IEEE
13 years 8 months ago
Scaling Up Multi-agent Reinforcement Learning in Complex Domains
TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (...
Dan Xiao, Ah-Hwee Tan
ESANN
2007
13 years 9 months ago
Replacing eligibility trace for action-value learning with function approximation
The eligibility trace is one of the most used mechanisms to speed up reinforcement learning. Earlier reported experiments seem to indicate that replacing eligibility traces would p...
Kary Främling
IWANN
1999
Springer
14 years 10 days ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson