notesum.ai
Published at November 15The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
cs.LG
cs.AI
cs.CV
Released Date: November 15, 2024
Authors: Moritz Schneider, Robert Krug, Narunas Vaskevicius, Luigi Palmieri, Joschka Boedecker

| # | Name | URL | License |
|---|---|---|---|
| 1 | CLIP | https://github.com/openai/CLIP | MIT |
| 2 | DinoV2 | https://github.com/facebookresearch/dinov2 | Apache 2.0 |
| 3 | OpenCLIP | https://github.com/facebookresearch/ImageBind | CC BY-NC-SA 4.0 DEED |
| 4 | R2D2 | https://github.com/naver/r2d2 | CC BY-NC-SA 3.0 DEED |
| 5 | R3M | https://github.com/facebookresearch/r3m | MIT |
| 6 | Taskonomy | https://github.com/alexsax/visual-prior | MIT |
| 7 | VC-1 | https://github.com/facebookresearch/eai-vc | CC BY-NC 4.0 DEED |
| 8 | VIP | https://github.com/facebookresearch/vip | CC BY-NC 4.0 DEED |