With fast 3D graphics becoming more and more available even on low end platforms, the focus in developing new graphics hardware is beginning to shift towards higher quality render...
The probability of failures in software distributed shared memory (SDSM) increases as the system size grows. This paper introduces a new, efficient message logging technique, call...
In this paper, we present a novel multi-agent learning paradigm called team-partitioned, opaque-transition reinforcement learning (TPOT-RL). TPOT-RL introduces the concept of usin...
A large number of database index structures have been proposed over the last two decades, and little consensus has emerged regarding their relative e ectiveness. In order to empir...
Joseph M. Hellerstein, Lisa Hellerstein, George Ko...
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...