SeqVAE: Sequence variational autoencoder with policy gradient
Sign Up to like & getrecommendations! Published in 2021 at "Applied Intelligence"
DOI: 10.1007/s10489-021-02374-7
Abstract: In the paper, we propose a variant of Variational Autoencoder (VAE) for sequence generation task, called SeqVAE, which is a combination of recurrent VAE and policy gradient in reinforcement learning. The goal of SeqVAE is… read more here.
Keywords: policy gradient; policy; seqvae; variational autoencoder ... See more keywords