169 search results - page 21 / 34 » Tractability of Planning with Loops |
JAIR
2006
13 years 6 months ago
2006
A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decisiontheoretic...
CI
2005
13 years 6 months ago
2005
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
ATAL
2005
Springer
14 years 8 days ago
2005
Springer
We present here Extended Markov Tracking (EMT), a computationally tractable method for the online estimation of Markovian system dynamics, along with experimental support for its ...
AAAI
1996
13 years 8 months ago
1996
The Airport Example The Omelette Example Copyright c 1996 American Association for Artificial Intelligence. All rights reserved. Despite the existence of programs that are able to ...
PDSE
2000
13 years 8 months ago
2000
The aim of this paper is to describe a generic interface through which a planning tool or design aid can be connected to a telecommunications network. In today's complex and ...