Sciweavers

242 search results - page 2 / 49
» Provably Bounded Optimal Agents
Sort
View
UAI
2001
13 years 6 months ago
Maximum Likelihood Bounded Tree-Width Markov Networks
We study the problem of projecting a distribution onto (or finding a maximum likelihood distribution among) Markov networks of bounded tree-width. By casting it as the combinatori...
Nathan Srebro
UAI
2000
13 years 6 months ago
The Complexity of Decentralized Control of Markov Decision Processes
We consider decentralized control of Markov decision processes and give complexity bounds on the worst-case running time for algorithms that find optimal solutions. Generalization...
Daniel S. Bernstein, Shlomo Zilberstein, Neil Imme...
EUROPAR
2008
Springer
13 years 7 months ago
Deque-Free Work-Optimal Parallel STL Algorithms
This paper presents provable work-optimal parallelizations of STL (Standard Template Library) algorithms based on the workstealing technique. Unlike previous approaches where a deq...
Daouda Traoré, Jean-Louis Roch, Nicolas Mai...
AIPS
2010
13 years 7 months 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
SIGECOM
2003
ACM
107views ECommerce» more  SIGECOM 2003»
13 years 10 months ago
Using value queries in combinatorial auctions
Combinatorial auctions, where bidders can bid on bundles of items are known to be desirable auction mechanisms for selling items that are complementary and/or substitutable. Howev...
Benoît Hudson, Tuomas Sandholm