Wind-field identification for parafoils based on deep Q-learning iterative inversion.

Zhenping Yu Hao Sun Qinglin Sun Jin Tao Zengqiang Chen

Published in: Inf. Sci. (2022)

Keyphrases

reinforcement learning
cooperative
multi agent
learning algorithm
data sets
learning rate
neural network
state space
least squares
dynamic environments
optimal policy
image reconstruction
markov decision processes
model free
stochastic approximation