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
Rohin Shah — most-cited papers & profile · Reinforcement Learning
← authors
·
overview
Rohin Shah
11
papers ·
43
citations ·
8
h-index
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Preferences Implicit in the State of the World
2019 · 15 citations
On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference
2019 · 14 citations
Evaluating the Robustness of Collaborative Agents
2021 · 8 citations
The MineRL BASALT Competition on Learning from Human Feedback
2021 · 4 citations
Optimal Policies Tend to Seek Power
2019 · 1 citations
MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking
2025
Top co-authors
Pieter Abbeel
· 3
Anca Dragan
· 2
Alexander Matt Turner
· 1
David Lindner
· 1
Dmitrii Krasheninnikov
· 1
Micah Carroll
· 1
Sam Devlin
· 1
Sebastian Farquhar
· 1
Vikrant Varma
· 1
Topics
Safe RL
RLHF & Alignment
Model-Based RL
Multi-Agent
Game AI
Value-Based
Exploration