374 search results - page 45 / 75 » Multiagent Reinforcement Learning: Theoretical Framework and... |
ICML
2009
IEEE
14 years 8 months ago
2009
IEEE
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in particular the Least-Squares Temporal Difference (L...
CCS
2009
ACM
14 years 2 months ago
2009
ACM
We propose a framework for quantitative security analysis of machine learning methods. Key issus of this framework are a formal specification of the deployed learning model and a...
ECML
2001
Springer
14 years 6 days ago
2001
Springer
When correct priors are known, Bayesian algorithms give optimal decisions, and accurate confidence values for predictions can be obtained. If the prior is incorrect however, these...
NIPS
2007
13 years 9 months ago
2007
Learning the common structure shared by a set of supervised tasks is an important practical and theoretical problem. Knowledge of this structure may lead to better generalization ...
JMLR
2006
13 years 7 months ago
2006
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...