Formal synthesis of distributed optimal traffic control policies.

Sadra Sadraddini János Rudan Calin Belta

Published in: ICCPS (2017)

Keyphrases

control policies
control policy
optimal policy
reinforcement learning
finite horizon
control system
dynamic programming
multi agent
stochastic optimization problems
probabilistic model
cooperative
control strategies
optimal solution
action space
motion control
real time
mobile robot
mathematical model