2100 search results - page 187 / 420 » Observation Can Be as Effective as Action in Problem Solving |
180
click to vote
ATAL
2008
Springer
15 years 8 months ago
2008
Springer
Reinforcement Learning research is traditionally devoted to solve single-task problems. Therefore, anytime a new task is faced, learning must be restarted from scratch. Recently, ...
205
click to vote
PLANX
2007
15 years 8 months ago
2007
We present an algorithm to solve XPath decision problems under regular tree type constraints and show its use to statically typecheck XPath queries. To this end, we prove the deci...
165
click to vote
KCAP
2003
ACM
15 years 11 months ago
2003
ACM
Many AI tasks require determining whether two knowledge representations encode the same knowledge. Solving this matching problem is hard because representations may encode the sam...
179
click to vote
ICTAI
2000
IEEE
15 years 10 months ago
2000
IEEE
Markov Decision Processes (MDP) have been widely used as a framework for planning under uncertainty. They allow to compute optimal sequences of actions in order to achieve a given...
218
click to vote
JAIR
2007
15 years 6 months ago
2007
In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-...