Connecting Generative Adversarial Networks and Actor-Critic Methods — mentioned by gwern

Tue, 27 Mar 2018 22:26:15 GMT

Depends on whether you see the glass half-full or half-empty. Is it a DRL actor-critic where the reward & critic happen to be half of a GAN, or is it a GAN where the generator happens to receive a RL-style loss instead of the normal discriminator loss? Actor-critic and GANs have always been hard to tell apart: https://arxiv.org/pdf/1610.01945.pdf

Paper and discussion history. A mention is not an endorsement.

Connecting Generative Adversarial Networks and Actor-Critic Methods · HackerPapers discussions

Connecting Generative Adversarial Networks and Actor-Critic Methods — mentioned by gwern