Sciweavers

378 search results - page 16 / 76
» Reinforcement Learning for Online Control of Evolutionary Al...
Sort
View
CCGRID
2007
IEEE
13 years 11 months ago
A Hybrid Linear Programming and Evolutionary Algorithm based Approach for On-line Resource Matching in Grid Environments
We describe a hybrid linear programming (LP) and evolutionary algorithm (EA) based resource matcher suitable for heterogeneous grid environments. The hybrid matcher adopts the ite...
Pawel Garbacki, Vijay K. Naik
EUSFLAT
2001
144views Fuzzy Logic» more  EUSFLAT 2001»
13 years 9 months ago
Adaptive torque control using a connectionist reinforcement learning agent
The correction of angular misalignment between mating components is a fundamental requirement for their successful assembly. In this paper we present how a learning agent based on...
Lorenzo Brignone, Martin Howarth, S. Sivayoganatha...
GECCO
2000
Springer
143views Optimization» more  GECCO 2000»
13 years 11 months ago
A Genetic Algorithm for Automatically Designing Modular Reinforcement Learning Agents
Reinforcement learning (RL) is one of the machine learning techniques and has been received much attention as a new self-adaptive controller for various systems. The RL agent auto...
Isao Ono, Tetsuo Nijo, Norihiko Ono
ATAL
2003
Springer
14 years 24 days ago
A selection-mutation model for q-learning in multi-agent systems
Although well understood in the single-agent framework, the use of traditional reinforcement learning (RL) algorithms in multi-agent systems (MAS) is not always justified. The fe...
Karl Tuyls, Katja Verbeeck, Tom Lenaerts
JMLR
2010
119views more  JMLR 2010»
13 years 2 months ago
A Convergent Online Single Time Scale Actor Critic Algorithm
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...
Dotan Di Castro, Ron Meir