A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Conditional random fields for multi-agent reinforcement learning
2007
Proceedings of the 24th international conference on Machine learning - ICML '07
Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of observation and label pairs. Underlying all CRFs is the assumption that, conditioned on the training data, the labels are independent and identically distributed (iid). In this paper we explore the use of CRFs in a class of temporal learning algorithms, namely policygradient reinforcement learning (RL). Now the labels are
doi:10.1145/1273496.1273640
dblp:conf/icml/ZhangAV07
fatcat:qm5uqf4emzgvbdlhzvssrgwgge