371 search results - page 47 / 75 » The Complexity of Decentralized Control of Markov Decision P... |
HYBRID
2010
Springer
15 years 6 months ago
2010
Springer
The complexity of physical and engineering systems, both in terms of the governing physical phenomena and the number of subprocesses involved, is mirrored in ever more complex mat...
103
click to vote
UAI
2004
15 years 1 months ago
2004
Although many real-world stochastic planning problems are more naturally formulated by hybrid models with both discrete and continuous variables, current state-of-the-art methods ...
119
click to vote
CN
2006
14 years 12 months ago
2006
Performance critical services over Internet often rely on geographically distributed architectures of replicated servers. Content Delivery Networks (CDN) are a typical example whe...
103
click to vote
AIPS
1998
15 years 1 months ago
1998
Planning methods for deterministic planning problems traditionally exploit factored representations to encode the dynamics of problems in terms of a set of parameters, e.g., the l...
159
click to vote
ILP
2007
Springer
15 years 6 months ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...