Efficient Solutions for Targeted Control of Multi-Agent MDPs.

Carmel Fiscko Soummya Kar Bruno Sinopoli

Published in: ACC (2021)

Keyphrases

efficient solutions
multi agent
reinforcement learning
bicriteria
markov decision processes
bi objective
heuristic methods
control system
optimal solution
optimal policy
optimal control
search algorithm
multi objective
dynamic programming
state space
cooperative
finite horizon