Combinatorial Reinforcement Learning of Linear Assignment Problems.

Sascha Hamzehi Klaus Bogenberger Philipp Franeck Bernd Kaltenhäuser

Published in: ITSC (2019)

Keyphrases

reinforcement learning
function approximators
function approximation
real time
machine learning
database

stochastic approximation
multi agent
optimal solution
closed form
robotic control
reinforcement learning algorithms

linear model
dynamical systems
transfer learning
optimal policy
state space
dynamic programming

learning process
lower bound
decision trees
social networks
information retrieval
neural network