1166 search results - page 121 / 234 » Negotiating Using Rewards |
107
click to vote
JNW
2007
15 years 2 months ago
2007
— Today, the most important aspect related with the Internet architecture is its ossification representing the difficulties to introduce evolutions in the architecture as a way...
CN
1998
15 years 2 months ago
1998
: We have modi ed the popular Mbone tool Vic (VIdeo Conferencing) to use Arequipa (Application REQuested IPoverATM). The latter enables applications and in particular Vic, to reque...
ICML
2006
IEEE
16 years 3 months ago
2006
IEEE
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
114
click to vote
ICML
2005
IEEE
16 years 3 months ago
2005
IEEE
The current framework of reinforcement learning is based on maximizing the expected returns based on scalar rewards. But in many real world situations, tradeoffs must be made amon...
104
click to vote
IJCNN
2008
IEEE
15 years 8 months ago
2008
IEEE
— In this paper we address the reliability of policies derived by Reinforcement Learning on a limited amount of observations. This can be done in a principled manner by taking in...