Sciweavers

1068 search results - page 94 / 214
» For completeness, sublogarithmic space is no space
Sort
View
AAAI
2010
13 years 10 months ago
Integrating Sample-Based Planning and Model-Based Reinforcement Learning
Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (e.g. DBNs) can be learned with tractable sample complexity, desp...
Thomas J. Walsh, Sergiu Goschin, Michael L. Littma...
GRAPHICSINTERFACE
2008
13 years 10 months ago
Lightweight task/application performance using single versus multiple monitors: a comparative study
It is becoming increasingly common to see computers with two or even three monitors being used today. People seem to like having more display space available, and intuition tells ...
Youn ah Kang, John T. Stasko
AAAI
2004
13 years 10 months ago
SAT-Based Answer Set Programming
The relation between answer set programming (ASP) and propositional satisfiability (SAT) is at the center of many research papers, partly because of the tremendous performance boo...
Enrico Giunchiglia, Yuliya Lierler, Marco Maratea
NIPS
2004
13 years 10 months ago
Limits of Spectral Clustering
An important aspect of clustering algorithms is whether the partitions constructed on finite samples converge to a useful clustering of the whole data space as the sample size inc...
Ulrike von Luxburg, Olivier Bousquet, Mikhail Belk...
AR
2007
105views more  AR 2007»
13 years 9 months ago
Reinforcement learning of a continuous motor sequence with hidden states
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sug...