Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach.

Mohammad Ali Alomrani Reza Moravej Elias B. Khalil

Published in: CoRR (2021)

Keyphrases

bipartite matching
reinforcement learning
optimal policy
online learning
function approximation
markov decision process
maximum weight
policy search
learning algorithm
dynamic programming
graphical models
markov decision processes
control policy
evolutionary algorithm
optimization algorithm
minimum cost flow