Sciweavers

7129 search results - page 944 / 1426
» Approximation Algorithms for Treewidth
Sort
View
NIPS
2001
15 years 6 months ago
Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Policy gradient methods for reinforcement learning avoid some of the undesirable properties of the value function approaches, such as policy degradation (Baxter and Bartlett, 2001...
Evan Greensmith, Peter L. Bartlett, Jonathan Baxte...
138
Voted
WSCG
2004
189views more  WSCG 2004»
15 years 6 months ago
Hardware Accelerated Soft Shadows using Penumbra Quads
Shadow mapping is a commonly used technique for generating hard shadows in real time. However, existing shadow map based algorithms cannot render full soft shadows penumbras onto ...
Jukka Arvo, Jan Westerholm
SODA
2003
ACM
158views Algorithms» more  SODA 2003»
15 years 6 months ago
Comparing top k lists
Motivated by several applications, we introduce various distance measures between “top k lists.” Some of these distance measures are metrics, while others are not. For each of...
Ronald Fagin, Ravi Kumar, D. Sivakumar
VCIP
2003
15 years 6 months ago
Three-dimensional mesh simplification using normal variation error metric and modified subdivided edge classification
In order to transmit or store three-dimensional (3-D) mesh models efficiently, we need to simplify them. Although the quadric error metric (QEM) provides fast and accurate geometr...
Eun-Young Chang, Chung-Hyun Ahn, Yo-Sung Ho
ATAL
2010
Springer
15 years 6 months ago
Point-based policy generation for decentralized POMDPs
Memory-bounded techniques have shown great promise in solving complex multi-agent planning problems modeled as DEC-POMDPs. Much of the performance gains can be attributed to pruni...
Feng Wu, Shlomo Zilberstein, Xiaoping Chen