93 search results - page 19 / 19 » Computing Optimal Policies for Partially Observable Decision... |
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
Reinforcement learning (RL) was originally proposed as a framework to allow agents to learn in an online fashion as they interact with their environment. Existing RL algorithms co...
HRI
2007
ACM
13 years 8 months ago
2007
ACM
Intelligent planning algorithms such as the Partially Observable Markov Decision Process (POMDP) have succeeded in dialog management applications [10, 11, 12] because of their rob...
CISS
2008
IEEE
13 years 11 months ago
2008
IEEE
Abstract—We consider adapting the transmission rate to maximize the goodput, i.e., the amount of data transmitted without error, over a continuous Markov flat-fading wireless ch...