102 search results - page 7 / 21 » Efficient Asymptotic Approximation in Temporal Difference Le... |
ATAL
2008
Springer
14 years 11 months ago
2008
Springer
In reinforcement learning, least-squares temporal difference methods (e.g., LSTD and LSPI) are effective, data-efficient techniques for policy evaluation and control with linear v...
NIPS
2007
14 years 11 months ago
2007
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
ICPR
2002
IEEE
15 years 10 months ago
2002
IEEE
This paper considers a recently proposed method for unsupervised learning and dimensionality reduction, locally linear embedding (LLE). LLE computes a compact representation of hi...
117
click to vote
UAI
2008
14 years 11 months ago
2008
Numerous temporal inference tasks such as fault monitoring and anomaly detection exhibit a persistence property: for example, if something breaks, it stays broken until an interve...
ICML
2004
IEEE
15 years 10 months ago
2004
IEEE
lative Novelty to Identify Useful Temporal Abstractions in Reinforcement Learning ?Ozg?ur S?im?sek ozgur@cs.umass.edu Andrew G. Barto barto@cs.umass.edu Department of Computer Scie...