Sciweavers

10054 search results - page 423 / 2011
» On the Complexity of Function Learning
Sort
View
IROS
2006
IEEE
100views Robotics» more  IROS 2006»
15 years 10 months ago
Sound Localization for Humanoid Robots - Building Audio-Motor Maps based on the HRTF
— Being able to localize the origin of a sound is important for our capability to interact with the environment. Humans can localize a sound source in both the horizontal and ver...
Jonas Hörnstein, Manuel Lopes, José Sa...
GECCO
2010
Springer
186views Optimization» more  GECCO 2010»
15 years 5 months ago
Genetic rule extraction optimizing brier score
Most highly accurate predictive modeling techniques produce opaque models. When comprehensible models are required, rule extraction is sometimes used to generate a transparent mod...
Ulf Johansson, Rikard König, Lars Niklasson
ICML
2000
IEEE
16 years 5 months ago
Eligibility Traces for Off-Policy Policy Evaluation
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
ICML
2009
IEEE
16 years 5 months ago
Learning spectral graph transformations for link prediction
We present a unified framework for learning link prediction and edge weight prediction functions in large networks, based on the transformation of a graph's algebraic spectru...
Andreas Lommatzsch, Jérôme Kunegis
ICML
2001
IEEE
16 years 5 months ago
Symmetry in Markov Decision Processes and its Implications for Single Agent and Multiagent Learning
This paper examines the notion of symmetry in Markov decision processes (MDPs). We define symmetry for an MDP and show how it can be exploited for more effective learning in singl...
Martin Zinkevich, Tucker R. Balch