55 search results - page 6 / 11 » Policy Tree: Adaptive Representation for Policy Gradient |
AAAI
1996
13 years 8 months ago
1996
Procedural representations of control policies have two advantages when facing the scale-up problem in learning tasks. First they are implicit, with potential for inductive genera...
NGC
2001
Springer
13 years 12 months ago
2001
Springer
Bi-directional shared tree is an efficient routing scheme for interactive multicast applications with multiple sources. Given the open-group IP multicast service model, it is impor...
LISA
2001
13 years 8 months ago
2001
After installing an OS distribution, a computer is generally not yet properly adapted to go into production at the local site. Security policies must be implemented, local service...
TVLSI
2008
13 years 7 months ago
2008
Thermal hot spots and high temperature gradients degrade reliability and performance, and increase cooling costs and leakage power. In this paper, we explore the benefits of temper...
AI
2000
Springer
13 years 7 months ago
2000
Springer
Markov decisionprocesses(MDPs) haveproven to be popular models for decision-theoretic planning, but standard dynamic programming algorithms for solving MDPs rely on explicit, stat...