Login / Signup
Data Driven State Reconstruction of Dynamical System Based on Approximate Dynamic Programming and Reinforcement Learning.
Fábio Nogueira da Silva
João Viana da Fonseca Neto
Published in:
IEEE Access (2021)
Keyphrases
</>
approximate dynamic programming
dynamical systems
reinforcement learning
state space
data driven
hidden state
dynamic programming
partially observable
linear program
control policy
differential equations
dynamical behavior
linear dynamical systems
predictive state representations
optimal policy
learning algorithm
fixed point
past observations
phase space
immune network
function approximation
markov chain
machine learning
reinforcement learning algorithms
step size
policy iteration
action space
markov decision processes
model free
nonlinear dynamical systems
particle filter
lower bound
evolutionary algorithm
supervised learning
linear programming
continuous state
markov decision process
belief state