Abstract. Recent theoretical work helped explain certain optimizationrelated pathologies in cooperative coevolutionary algorithms (CCEAs). Such explanations have led to adopting sp...
—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 ...
— 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...
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...
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...