Sciweavers

9284 search results - page 76 / 1857
» Knowledge State Algorithms
Sort
View
VLSID
1999
IEEE
87views VLSI» more  VLSID 1999»
15 years 4 months ago
Optimal Retiming for Initial State Computation
Retiming is a transformation that optimizes a sequential circuit by relocating the registers. When the circuit has an initial state, one must compute an equivalent initial state f...
Peichen Pan, Guohua Chen
ICML
2000
IEEE
16 years 20 days ago
Reinforcement Learning in POMDP's via Direct Gradient Ascent
This paper discusses theoretical and experimental aspects of gradient-based approaches to the direct optimization of policy performance in controlled ??? ?s. We introduce ??? ?, a...
Jonathan Baxter, Peter L. Bartlett
IROS
2009
IEEE
163views Robotics» more  IROS 2009»
15 years 6 months ago
On the performance of random linear projections for sampling-based motion planning
— Sampling-based motion planners are often used to solve very high-dimensional planning problems. Many recent algorithms use projections of the state space to estimate properties...
Ioan Alexandru Sucan, Lydia E. Kavraki
DALT
2005
Springer
15 years 5 months ago
An Architecture for Rational Agents
Abstract. This paper is concerned with designing architectures for rational agents. In the proposed architecture, agents have belief bases that are theories in a multi-modal, highe...
John W. Lloyd, Tim D. Sears
NIPS
2007
15 years 1 months ago
A Spectral Regularization Framework for Multi-Task Structure Learning
Learning the common structure shared by a set of supervised tasks is an important practical and theoretical problem. Knowledge of this structure may lead to better generalization ...
Andreas Argyriou, Charles A. Micchelli, Massimilia...