TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Image Augmentation Is All You Need: Regularizing Deep Reinf Learning Fr Pixels

1 点作者 overfitted大约 5 年前

1 comment

overfitted大约 5 年前
<i>We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages input perturbations commonly used in computer vision tasks to regularize the value function. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SAC&#x27;s performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Dreamer, SLAC, PlaNet) methods and recently proposed contrastive learning (CURL). Our approach can be combined with any model-free reinforcement learning algorithm, requiring only minor modifications.</i> - Ilya Kostrikov, Denis Yarats, Rob Fergus