Policy gradient approaches for multi-objective sequential decision making.

Simone Parisi Matteo Pirotta Nicola Smacchia Luca Bascetta Marcello Restelli

Published in: IJCNN (2014)

Keyphrases

multi objective
sequential decision making
genetic algorithm
optimization algorithm
policy gradient
reinforcement learning
objective function
evolutionary algorithm
multi objective optimization
neural network
data mining
dynamic programming
decision problems
influence diagrams