首页/论文/2007.09180

arXiv 2007.091802020-07-17cs.CV

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

ETH Zürich（苏黎世联邦理工学院）；UESTC（电子科技大学）；Navinfo Europe（欧洲四维图新）；University College London（伦敦大学学院）

Yuan Tian, Qin Wang, Zhiwu Huang, Wen Li, Dengxin Dai, Minghao Yang, Jun Wang, Olga Fink

备注：: To appear in ECCV 2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Learning a Deep Reinforcement Learning Policy Over the Latent Space of a Pre-trained GAN for Semantic Age Manipulation

International Institute of Information Technology, Bangalore（国际信息技术学院班加罗尔分校）；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）

Learning a disentangled representation of the latent space has become one of the most fundamental problems studied in computer vision. Recently, many Generative Adversarial Networks (GANs) have shown promising results in generating high fidelity images. However, studies to understand the semantic layout of the latent space of pre-trained models are still limited. Several works train conditional GANs to generate faces with required semantic attributes. Unfortunately, in these attempts, the generated output is often not as photo-realistic as the unconditional state-of-the-art models. Besides, th…

2021-04-28cs.CV

通过强化学习控制GAN的潜在空间：基于任务的图像到图像翻译案例研究

Controlling the Latent Space of GANs through Reinforcement Learning: A Case Study on Task-based Image-to-Image Translation

University of California, Irvine（加州大学欧文分校）；Stanford University（斯坦福大学）；Toyota Motor North America（丰田汽车北美公司）

本文提出将强化学习智能体与潜在空间GAN结合，通过精心设计的奖励策略控制生成过程，并在MNIST数据集上验证了该方法在基于任务的图像生成中的有效性。

2023-07-26cs.AIcs.CVcs.LG

GAN-based Intrinsic Exploration For Sample Efficient Reinforcement Learning

Istanbul Technical University（伊斯坦布尔理工大学）

In this study, we address the problem of efficient exploration in reinforcement learning. Most common exploration approaches depend on random action selection, however these approaches do not work well in environments with sparse or no rewards. We propose Generative Adversarial Network-based Intrinsic Reward Module that learns the distribution of the observed states and sends an intrinsic reward that is computed as high for states that are out of distribution, in order to lead agent to unexplored states. We evaluate our approach in Super Mario Bros for a no reward setting and in Montezuma's Re…

2022-06-28cs.AIcs.CVcs.LG

Automated Augmentation with Reinforcement Learning and GANs for Robust Identification of Traffic Signs using Front Camera Images

Volvo Cars USA（沃尔沃汽车美国公司）；U. Washington（华盛顿大学）；VolvoCars（沃尔沃汽车）；Chalmers University of Technology（查尔姆斯理工大学）；Fung Institute, University of California, Berkeley（加州大学伯克利分校冯氏研究所）

Traffic sign identification using camera images from vehicles plays a critical role in autonomous driving and path planning. However, the front camera images can be distorted due to blurriness, lighting variations and vandalism which can lead to degradation of detection performances. As a solution, machine learning models must be trained with data from multiple domains, and collecting and labeling more data in each new domain is time consuming and expensive. In this work, we present an end-to-end framework to augment traffic sign training data using optimal reinforcement learning policies and …

2019-11-15cs.AIcs.CVcs.LG

强化学习环境中基于 GAN 的自顶向下视图合成

GAN Based Top-Down View Synthesis in Reinforcement Learning Environments

University of Maryland, College Park（马里兰大学帕克分校）

本项目利用生成对抗网络（GAN）基于人工智能体的第一人称视角观察合成强化学习环境的自顶向下视图，以辅助智能体推断更好的策略决策，但不涉及具体强化学习任务。

2024-10-16cs.CVcs.SYeess.SY

基于策略梯度的少样本学习视频到视频生成对抗网络

Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient

Northwestern University（西北大学）；Allstate Insurance Company（好事达保险公司）

本文提出 RL-V2V-GAN，结合策略梯度、ConvLSTM 与细粒度时空 GAN，实现无需成对输入的无监督条件视频到视频合成，并在少样本目标域中生成时间连贯视频。

2024-10-28cs.CVcs.LG

更多相关论文收起更多论文

RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion

KAIST（韩国科学技术院）；KIST（韩国科学技术研究院）；SNU（首尔大学）

We present RL-GAN-Net, where a reinforcement learning (RL) agent provides fast and robust control of a generative adversarial network (GAN). Our framework is applied to point cloud shape completion that converts noisy, partial point cloud data into a high-fidelity completed shape by controlling the GAN. While a GAN is unstable and hard to train, we circumvent the problem by (1) training the GAN on the latent space representation whose dimension is reduced compared to the raw point cloud input and (2) using an RL agent to find the correct input to the GAN to generate the latent space representa…

2019-04-28cs.AIcs.CV

Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video

Sun Yat-sen University（中山大学）；Beihang University（北京航空航天大学）；DarkMatter AI Research（DarkMatter AI研究院）

Temporally language grounding in untrimmed videos is a newly-raised task in video understanding. Most of the existing methods suffer from inferior efficiency, lacking interpretability, and deviating from the human perception mechanism. Inspired by human's coarse-to-fine decision-making paradigm, we formulate a novel Tree-Structured Policy based Progressive Reinforcement Learning (TSP-PRL) framework to sequentially regulate the temporal boundary by an iterative refinement process. The semantic concepts are explicitly represented as the branches in the policy, which contributes to efficiently de…

2020-01-18cs.CV

Partial Policy-based Reinforcement Learning for Anatomical Landmark Localization in 3D Medical Images

Hankuk University of Foreign Studies

Deploying the idea of long-term cumulative return, reinforcement learning has shown remarkable performance in various fields. We propose a formulation of the landmark localization in 3D medical images as a reinforcement learning problem. Whereas value-based methods have been widely used to solve similar problems, we adopt an actor-critic based direct policy search method framed in a temporal difference learning approach. Successful behavior learning is challenging in large state and/or action spaces, requiring many trials. We introduce a partial policy-based reinforcement learning to enable so…

2018-12-31cs.CVcs.LG

Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning

UC Berkeley（加州大学伯克利分校）

We propose a new policy parameterization for representing 3D rotations during reinforcement learning. Today in the continuous control reinforcement learning literature, many stochastic policy parameterizations are Gaussian. We argue that universally applying a Gaussian policy parameterization is not always desirable for all environments. One such case in particular where this is true are tasks that involve predicting a 3D rotation output, either in isolation, or coupled with translation as part of a full 6D pose output. Our proposed Bingham Policy Parameterization (BPP) models the Bingham dist…

2022-02-08cs.AIcs.CVcs.LG

Policy Augmentation: An Exploration Strategy for Faster Convergence of Deep Reinforcement Learning Algorithms

Florida Institute for Human and Machine Cognition (IHMC)（佛罗里达人机认知研究所（IHMC））

Despite advancements in deep reinforcement learning algorithms, developing an effective exploration strategy is still an open problem. Most existing exploration strategies either are based on simple heuristics, or require the model of the environment, or train additional deep neural networks to generate imagination-augmented paths. In this paper, a revolutionary algorithm, called Policy Augmentation, is introduced. Policy Augmentation is based on a newly developed inductive matrix completion method. The proposed algorithm augments the values of unexplored state-action pairs, helping the agent …

2021-02-10cs.AIcs.CVcs.LG