Exploiting Fast Decaying and Locality in Multi-Agent MDP with Tree Dependence Structure.

Guannan Qu Na Li

Published in: CDC (2019)

Keyphrases

dependence structure
multi agent
reinforcement learning
markov decision processes
optimal policy
marginal distributions
markov decision process
markov networks
higher order statistics
multiscale
multiresolution
state space
domain specific
text classification