Optimizing Attention for Sequence Modeling via Reinforcement Learning.

Hao Fei Yue Zhang Yafeng Ren Donghong Ji

Published in: IEEE Trans. Neural Networks Learn. Syst. (2022)

Keyphrases

reinforcement learning
hidden state
objective function
multi agent
visual attention
neural network
learning algorithm
artificial intelligence
information systems
decision making
hidden markov models
markov decision processes
model free
modeling method
partially observable