113 search results - page 20 / 23 » Learning Representation and Control in Continuous Markov Dec... |
PKDD
2010
Springer
13 years 7 months ago
2010
Springer
Abstract. One of the key problems in model-based reinforcement learning is balancing exploration and exploitation. Another is learning and acting in large relational domains, in wh...
ICML
2007
IEEE
14 years 9 months ago
2007
IEEE
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
ATAL
2010
Springer
13 years 10 months ago
2010
Springer
Decentralized reinforcement learning (DRL) has been applied to a number of distributed applications. However, one of the main challenges faced by DRL is its convergence. Previous ...
AIR
2005
13 years 9 months ago
2005
Because of the changing nature of spam, a spam filtering system that uses machine learning will need to be dynamic. This suggests that a case-based (memory-based) approach may work...
AAAI
2000
13 years 10 months ago
2000
Given a model of a physical process and a sequence of commands and observations received over time, the task of an autonomous controller is to determine the likely states of the p...