Generative Flow Networks as Entropy-Regularized RL.

Daniil Tiapkin Nikita Morozov Alexey Naumov Dmitry P. Vetrov

Published in: AISTATS (2024)

Keyphrases

reinforcement learning
mutual information
generative model
information theoretic
optimal policy
function approximation
genetic algorithm
complex networks
information theory
information flow
flow patterns
neural network
multi agent
learning process
discriminative learning
risk minimization