Reinforcement Learning
stable-baselines3
deep-reinforcement-learning
mujoco
Hopper-v4
weight-editing
Eval Results (legacy)
Instructions to use erickvs/sac-Hopper-v4-hand-edited with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use erickvs/sac-Hopper-v4-hand-edited with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="erickvs/sac-Hopper-v4-hand-edited", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
Commit History
8 days ago
-
Add a narrated video explaining the edit
Verified signaturee046f8c
10 days ago
-
Link the WSP Lab waitlist at wsp-lab.ai
Verified signatured12a6f4 -
Card: name the zoo agents compared instead of claiming all of the zoo
Verified signaturee06e0d2 -
Card: actual release time
Verified signature7372648 -
Hand-edited SAC hopper: 98% falls to none, no training (made with WSP Lab)
Verified signature56ff781 -
initial commit
Verified signaturec9924d0