27 search results - page 4 / 6 » Improved Rates for the Stochastic Continuum-Armed Bandit Pro... |
GECCO
2004
Springer
14 years 14 days ago
2004
Springer
Abstract. Recent theoretical work helped explain certain optimizationrelated pathologies in cooperative coevolutionary algorithms (CCEAs). Such explanations have led to adopting sp...
CISS
2010
IEEE
12 years 10 months ago
2010
IEEE
—We consider broadcasting from a single source to multiple destinations in a linear wireless erasure network with feedback. The problem is to find the maximum stable throughput ...
ICRA
2010
IEEE
13 years 5 months ago
2010
IEEE
— Reinforcement learning (RL) is one of the most general approaches to learning control. Its applicability to complex motor systems, however, has been largely impossible so far d...
JMLR
2010
13 years 1 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
NLE
2007
13 years 6 months ago
2007
We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...