Shengyi Costa Huang

vwxyzjn's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 5 papers 6 months ago

The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization

Paper • 2403.17031 • Published Mar 24, 2024 • 6

A2C is a special case of PPO

Paper • 2205.09123 • Published May 18, 2022 • 1

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Paper • 2410.18252 • Published Oct 23, 2024 • 7

TÜLU 3: Pushing Frontiers in Open Language Model Post-Training

Paper • 2411.15124 • Published Nov 22, 2024 • 65

2 OLMo 2 Furious

Paper • 2501.00656 • Published Dec 31, 2024 • 19

authored 3 papers over 1 year ago

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

Paper • 2402.03046 • Published Feb 5, 2024 • 6

Zephyr: Direct Distillation of LM Alignment

Paper • 2310.16944 • Published Oct 25, 2023 • 122

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Paper • 2310.00036 • Published Sep 29, 2023 • 2

authored 2 papers almost 2 years ago

CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms

Paper • 2111.08819 • Published Nov 16, 2021 • 2

A Closer Look at Invalid Action Masking in Policy Gradient Algorithms

Paper • 2006.14171 • Published Jun 25, 2020