2011 search results - page 284 / 403 » Universal Reinforcement Learning |
CL
2000
Springer
14 years 20 days ago
2000
Springer
In this paper I give a brief overview of recent work on uncertainty inAI, and relate it to logical representations. Bayesian decision theory and logic are both normative frameworks...
DEXAW
1999
IEEE
14 years 20 days ago
1999
IEEE
This paper presents two metrics for the Nearest Neighbor Classifier that share the property of being adapted, i.e. learned, on a set of data. Both metrics can be used for similari...
ATAL
2006
Springer
14 years 2 days ago
2006
Springer
This paper studies scalable data delivery algorithms in mobile ad hoc sensor networks with node and link failures. Many algorithms have been developed for data delivery and fusion...
GECCO
2006
Springer
14 years 51 min ago
2006
Springer
This paper introduces XCSF extended with tile coding prediction: each classifier implements a tile coding approximator; the genetic algorithm is used to adapt both classifier cond...
AAAI
2008
13 years 10 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...