Sciweavers

Share
ICML
2007
IEEE

Conditional random fields for multi-agent reinforcement learning

10 years 26 days ago
Conditional random fields for multi-agent reinforcement learning
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 no longer iid. They are actions that update the environment and affect the next observation. From an RL point of view, CRFs provide a natural way to model joint actions in a decentralized Markov decision process. They define how agents can communicate with each other to choose the optimal joint action. Our experiments include a synthetic network alignment problem, a distributed sensor network, and road traffic control; clearly outperforming RL methods which do not model the proper joint policy.
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2007
Where ICML
Authors Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanathan
Comments (0)
books