Awesome Reinforcement Learning
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Oleksii Kuchaiev — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Oleksii Kuchaiev
14
papers ·
299
citations ·
0
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
2023 · 7 citations
HelpSteer2: Open-source dataset for training top-performing reward models
2024 · 2 citations
Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
2025
RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
2025
Top co-authors
Jiaqi Zeng
· 3
Makesh Narsimhan Sreedhar
· 3
Zhilin Wang
· 3
Daniel Egert
· 2
Gerald Shen
· 2
Olivier Delalleau
· 2
Alexander Bukharin
· 1
David Mosallanezhad
· 1
Di Zhang
· 1
Ellie Evans
· 1
Felipe Soares
· 1
Guilin Liu
· 1
Topics
RLHF & Alignment
Model-Based RL
Exploration
Policy Gradient