Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search

TL;DR

This paper presents an off-policy reinforcement learning approach for neural architecture search in GANs, achieving high-quality architectures with significantly reduced computational cost on standard benchmarks.

Contribution

It introduces a novel off-policy RL-based NAS method for GANs, improving efficiency and effectiveness in architecture discovery.

Findings

Achieved competitive GAN architectures with only 7 GPU hours

Demonstrated superior image generation on CIFAR-10 and STL-10

Reduced computational resources compared to existing methods

Abstract

In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search. The key idea is to formulate the GAN architecture search problem as a Markov decision process (MDP) for smoother architecture sampling, which enables a more effective RL-based search algorithm by targeting the potential global optimal architecture. To improve efficiency, we exploit an off-policy GAN architecture search algorithm that makes efficient use of the samples generated by previous policies. Evaluation on two standard benchmark datasets (i.e., CIFAR-10 and STL-10) demonstrates that the proposed method is able to discover highly competitive architectures for generally better image generation results with a considerably reduced computational burden: 7 GPU hours. Our code is available at https://github.com/Yuantian013/E2GAN.