1325 search results - page 137 / 265 » Algorithm Selection using Reinforcement Learning |
114
click to vote
NECO
2008
15 years 2 months ago
2008
Iterative learning algorithms that approximate the solution of support vector machines (SVMs) have two potential advantages. First, they allow for online and active learning. Seco...
77
Voted
AAAI
2008
15 years 4 months ago
2008
Hierarchical state decompositions address the curse-ofdimensionality in Q-learning methods for reinforcement learning (RL) but can suffer from suboptimality. In addressing this, w...
106
click to vote
IJCNN
2007
IEEE
15 years 9 months ago
2007
IEEE
– Constructive algorithms are effective methods for designing Artificial Neural Networks (ANN) with good accuracy and generalization capability, yet with parsimonious network str...
116
click to vote
ATAL
2008
Springer
15 years 4 months ago
2008
Springer
Reward shaping is a well-known technique applied to help reinforcement-learning agents converge more quickly to nearoptimal behavior. In this paper, we introduce social reward sha...
110
Voted
AAAI
2010
15 years 4 months ago
2010
Embedded systems consisting of collaborating agents capable of interacting with their environment are becoming ubiquitous. It is crucial for these systems to be able to adapt to t...