🎯 强化学习 - ice · Scour

PyTorch DevLog 🧠大模型微调

docs.pytorch.org·5d·Hacker News

Iran Names Internet Chief As Shutdown Reaches 75 Days 🛠️独立开发

sanantoniopost.com·3d

Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning 👁️多模态AI

Welcome 🔭科技趋势

onionui.github.io·21h

Qalibaf Says US 'Has No Alternative' But To Accept Iran's Terms 🛠️独立开发

parisguardian.com·4d

기술 뉴스 #294 : 26-05-16 🔭科技趋势

blog.outsider.ne.kr·18h

Gradient Bang - 一款通过与大型语言模型对话进行的游戏 👁️多模态AI

producthunt.com

·21h

Reinforcement Learning, Agency and Taste 👁️多模态AI

lesswrong.com·4d

イーロン・マスク氏、パヨクに言及「左派の根本的な道徳的欠陥は、犯罪者への共感はあっても被害者への共感がないこと」 ⏱️个人效率

moeasia.net·22h

PPO vs SAC Sparse Rewards: 3x Sample Efficiency Gap 👁️多模态AI

tildalice.io·3d

Jannik Sinner beats Daniil Medvedev to reach Italian Open final after overnight rain delay ✍人物传记、手工创作

·12h

Prompt caching but for RL – 7.5x speedup on long-prompt/short-response workloads 👁️多模态AI

castform.com·5d·Hacker News

Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation 👁️多模态AI

How Dirty Frag rose from the Copy Fail exploit ⏱️个人效率

reversinglabs.com·4d

🐎 💨 🚀科技创始人

youtube.com·13h

🎲 Study ✍人物传记、手工创作

jeankapsa.com·21h

☕️ Commencing with AI 👁️多模态AI

Morning Brew via kill-the-newsletter.com·17h

Former NFL defensive lineman Josh Mauro died from fentanyl, cocaine, ethanol overdose 📷计算机视觉

·8h

Some recent articles on language and linguistics 🎙️语音交互

languagelog.ldc.upenn.edu·5h

AIS: Adaptive Importance Sampling for Quantized RL 👁️多模态AI

Log in to enable infinite scrolling