Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Multimodal Interpretability/
RL Vision Interpretability
Search

RL Vision Interpretability

Creator
Creator
Seonglae Cho
Created
Created
2025 Feb 4 10:18
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Feb 4 11:6
Refs
Refs
Procgen
understanding-rl-vision
openai • Updated 2025 Jan 3 21:53
 
 
 
 
PPO
GAE
integrated gradients →
NMF
→ attribute extraction/editing
notion image
Understanding RL Vision
With diverse environments, we can analyze, diagnose and edit deep reinforcement learning models using attribution.
https://distill.pub/2020/understanding-rl-vision/
Understanding RL Vision
Procgen Benchmark
We’re releasing Procgen Benchmark, 16 simple-to-use procedurally-generated environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills.
Procgen Benchmark
https://openai.com/index/procgen-benchmark/
Procgen Benchmark
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Multimodal Interpretability/
RL Vision Interpretability
Copyright Seonglae Cho