Sciweavers

246 search results - page 9 / 50
» Approximate Predictive Representations of Partially Observab...
Sort
View
ICML
2009
IEEE
14 years 8 months ago
Predictive representations for policy gradient in POMDPs
We consider the problem of estimating the policy gradient in Partially Observable Markov Decision Processes (POMDPs) with a special class of policies that are based on Predictive ...
Abdeslam Boularias, Brahim Chaib-draa
PAMI
2010
248views more  PAMI 2010»
13 years 6 months ago
Coupled Prediction Classification for Robust Visual Tracking
—This paper addresses the problem of robust template tracking in image sequences. Our work falls within the discriminative framework in which the observations at each frame yield...
Ioannis Patras, Edwin R. Hancock
FOCS
2007
IEEE
14 years 2 months ago
Approximation Algorithms for Partial-Information Based Stochastic Control with Markovian Rewards
We consider a variant of the classic multi-armed bandit problem (MAB), which we call FEEDBACK MAB, where the reward obtained by playing each of n independent arms varies according...
Sudipto Guha, Kamesh Munagala
HICSS
2003
IEEE
207views Biometrics» more  HICSS 2003»
14 years 29 days ago
Formalizing Multi-Agent POMDP's in the context of network routing
This paper uses partially observable Markov decision processes (POMDP’s) as a basic framework for MultiAgent planning. We distinguish three perspectives: first one is that of a...
Bharaneedharan Rathnasabapathy, Piotr J. Gmytrasie...
AAAI
2004
13 years 9 months ago
An Instance-Based State Representation for Network Repair
We describe a formal framework for diagnosis and repair problems that shares elements of the well known partially observable MDP and cost-sensitive classification models. Our cost...
Michael L. Littman, Nishkam Ravi, Eitan Fenson, Ri...