An augmented MDP approach for solving Stochastic Security Games.

Romain Châtel Abdel-Illah Mouaddib

Published in: IROS (2021)

Keyphrases

markov decision processes
finite state
markov decision problems
policy iteration algorithm
state space
monte carlo
dynamic programming algorithms
optimal policy
linear program
combinatorial optimization
neural network
artificial neural networks
linear programming
stochastic optimization
transition matrices