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。

Making Real-World Reinforcement Learning Practical [video]

59 点作者 MAXPOOL超过 1 年前

1 comment

MAXPOOL超过 1 年前
Jan 3, 2024 Lecture by Sergey Levine about progress on real-world deep RL. Covers these papers:<p>A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning<p>Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion<p>Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Intervention<p>REBOOT: Reuse Data for Bootstrapping Efficient Real-World Dexterous Manipulation<p>FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing: <a href="https:&#x2F;&#x2F;sites.google.com&#x2F;view&#x2F;fastrlap" rel="nofollow">https:&#x2F;&#x2F;sites.google.com&#x2F;view&#x2F;fastrlap</a><p>Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions: <a href="https:&#x2F;&#x2F;qtransformer.github.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;qtransformer.github.io&#x2F;</a><p>Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators: <a href="https:&#x2F;&#x2F;rl-at-scale.github.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;rl-at-scale.github.io&#x2F;</a>
评论 #38891006 未加载