Sciweavers

179 search results - page 21 / 36
» Space Bounded Computations: Review And New Separation Result...
Sort
View
ICML
2006
IEEE
15 years 11 months ago
PAC model-free reinforcement learning
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
Alexander L. Strehl, Lihong Li, Eric Wiewiora, Joh...
84
Voted
MICRO
2009
IEEE
129views Hardware» more  MICRO 2009»
15 years 5 months ago
Execution leases: a hardware-supported mechanism for enforcing strong non-interference
High assurance systems such as those found in aircraft controls and the financial industry are often required to handle a mix of tasks where some are niceties (such as the contro...
Mohit Tiwari, Xun Li, Hassan M. G. Wassel, Frederi...
ICCV
2009
IEEE
16 years 3 months ago
Globally Optimal Affine Epipolar Geometry from Apparent Contours
We study the problem of estimating the epipolar geometry from apparent contours of smooth curved surfaces with affine camera models. Since apparent contours are viewpoint depend...
Gang Li, Yanghai Tsin
ICDCS
2006
IEEE
15 years 4 months ago
Routing in Networks with Low Doubling Dimension
This paper studies compact routing schemes for networks with low doubling dimension. Two variants are explored, name-independent routing and labeled routing. The key results obtai...
Ittai Abraham, Cyril Gavoille, Andrew V. Goldberg,...
AIPS
2010
15 years 25 days ago
When Policies Can Be Trusted: Analyzing a Criteria to Identify Optimal Policies in MDPs with Unknown Model Parameters
Computing a good policy in stochastic uncertain environments with unknown dynamics and reward model parameters is a challenging task. In a number of domains, ranging from space ro...
Emma Brunskill