Stochastic Actor-Executor-Critic for Image-to-Image Translation
This addresses the problem of high-dimensional continuous control in image-to-image translation for AI researchers, but it appears incremental as it adapts existing reinforcement learning frameworks to this domain.
The paper tackles the challenge of training model-free deep reinforcement learning for image-to-image translation in high-dimensional continuous spaces by proposing the Stochastic Actor-Executor-Critic (SAEC) method, which demonstrates effectiveness and robustness in experiments on several tasks.
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces. In this paper, we draw inspiration from the recent success of the maximum entropy reinforcement learning framework designed for challenging continuous control problems to develop stochastic policies over high dimensional continuous spaces including image representation, generation, and control simultaneously. Central to this method is the Stochastic Actor-Executor-Critic (SAEC) which is an off-policy actor-critic model with an additional executor to generate realistic images. Specifically, the actor focuses on the high-level representation and control policy by a stochastic latent action, as well as explicitly directs the executor to generate low-level actions to manipulate the state. Experiments on several image-to-image translation tasks have demonstrated the effectiveness and robustness of the proposed SAEC when facing high-dimensional continuous space problems.