MPC-Inspired Neural Network Policies for Sequential Decision Making.

Marcus Pereira David D. Fan Gabriel Nakajima An Evangelos A. Theodorou

Published in: CoRR (2018)

Keyphrases

sequential decision making
neural network
decision problems
reinforcement learning
optimal policy
interactive dynamic influence diagrams

influence diagrams
back propagation
artificial neural networks
state space
decision making
neural network model

genetic algorithm
multilayer perceptron
function approximation
multi agent
objective function

radial basis function
closed loop
reward function
expected utility
artificial intelligence