Sciweavers

282 search results - page 36 / 57
» Online Learning of Approximate Dependency Parsing Algorithms
Sort
View
ECML
2007
Springer
13 years 11 months ago
Efficient Continuous-Time Reinforcement Learning with Adaptive State Graphs
Abstract. We present a new reinforcement learning approach for deterministic continuous control problems in environments with unknown, arbitrary reward functions. The difficulty of...
Gerhard Neumann, Michael Pfeiffer, Wolfgang Maass
ECAI
2006
Springer
13 years 11 months ago
Least Squares SVM for Least Squares TD Learning
Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
Tobias Jung, Daniel Polani
IMC
2009
ACM
14 years 2 months ago
Scalable proximity estimation and link prediction in online social networks
Proximity measures quantify the closeness or similarity between nodes in a social network and form the basis of a range of applications in social sciences, business, information t...
Han Hee Song, Tae Won Cho, Vacha Dave, Yin Zhang, ...
PKDD
2010
Springer
179views Data Mining» more  PKDD 2010»
13 years 5 months ago
Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
Tobias Jung, Peter Stone
ESANN
2000
13 years 9 months ago
An algorithm for the addition of time-delayed connections to recurrent neural networks
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
Romuald Boné, Michel Crucianu, Jean Pierre ...