252 search results - page 22 / 51 » Learning Partially Observable Action Models: Efficient Algor... |
145
click to vote
AIIDE
2009
15 years 4 days ago
2009
This paper proposes an Integrated MDP and POMDP Learning AgeNT (IMPLANT) architecture for adaptation in modern games. The modern game world basically involves a human player actin...
115
click to vote
JAIR
2008
15 years 2 months ago
2008
Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains. However, solving a POMDP i...
114
Voted
AIPS
2008
15 years 4 months ago
2008
We consider the problem of cooperative multiagent planning under uncertainty, formalized as a decentralized partially observable Markov decision process (Dec-POMDP). Unfortunately...
124
Voted
AAAI
1992
15 years 3 months ago
1992
It is often useful for a robot to construct a spatial representation of its environment from experiments and observations, in other words, to learn a map of its environment by exp...
150
Voted
AVSS
2009
IEEE
15 years 5 months ago
2009
IEEE
—Automatic understanding of human behavior is an important and challenging objective in several surveillance applications. One of the main problems of this task consists in accur...