Sciweavers

32 search results - page 4 / 7
» Batch Reinforcement Learning with State Importance
Sort
View
93
Voted
ICAC
2008
IEEE
15 years 3 months ago
Utility-Based Reinforcement Learning for Reactive Grids
—Large scale production grids are an important case for autonomic computing. They follow a mutualization paradigm: decision-making (human or automatic) is distributed and largely...
Julien Perez, Cécile Germain-Renaud, Bal&aa...
86
Voted
NIPS
1996
14 years 10 months ago
Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone Systems
In cellular telephone systems, an important problem is to dynamically allocate the communication resource channels so as to maximize service in a stochastic caller environment. Th...
Satinder P. Singh, Dimitri P. Bertsekas
ECAL
2005
Springer
15 years 3 months ago
The Quantitative Law of Effect is a Robust Emergent Property of an Evolutionary Algorithm for Reinforcement Learning
An evolutionary reinforcement-learning algorithm, the operation of which was not associated with an optimality condition, was instantiated in an artificial organism. The algorithm ...
J. J. McDowell, Zahra Ansari
NIPS
2008
14 years 11 months ago
Optimization on a Budget: A Reinforcement Learning Approach
Many popular optimization algorithms, like the Levenberg-Marquardt algorithm (LMA), use heuristic-based "controllers" that modulate the behavior of the optimizer during ...
Paul Ruvolo, Ian R. Fasel, Javier R. Movellan
IROS
2008
IEEE
165views Robotics» more  IROS 2008»
15 years 3 months ago
Mutual development of behavior acquisition and recognition based on value system
Abstract. Both self-learning architecture (embedded structure) and explicit/implicit teaching from other agents (environmental design issue) are necessary not only for one behavior...
Yasutake Takahashi, Yoshihiro Tamura, Minoru Asada