Downloads · 30 days
0
0% of all-time downloads
half-cheetah-local-sac-test
Lonelyguyse1/half-cheetah-local-sac-test
half-cheetah-local-sac-test is a reinforcement learning model from Lonelyguyse1. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3.
Stable Baselines3 SAC policy trained on Gymnasium HalfCheetah-v5.
All-time downloads
35
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.md1.6 KB · 51%
At a glance
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Access
- Public
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026
- SHA
- 4f1ddd6c
Model card
From the Hugging Face model README
SAC HalfCheetah-v5
Stable Baselines3 SAC policy trained on Gymnasium HalfCheetah-v5.
The environment includes a small anti-flip reward guard to discourage belly-slide exploit postures.
Videos
Before training
<video controls src="https://huggingface.co/Lonelyguyse1/half-cheetah-local-sac-test/resolve/main/videos/initial.mp4"></video>
After training
<video controls src="https://huggingface.co/Lonelyguyse1/half-cheetah-local-sac-test/resolve/main/videos/final.mp4"></video>
What Was Done
- Trained SAC with
MlpPolicyfor300000timesteps. - Recorded a random policy rollout before training.
- Recorded the trained policy rollout after training.
- Saved the trained checkpoint as
sac_half_cheetah.zip.
Evaluation
Single deterministic rollout with seed 8.
| Metric | Value |
|---|---|
| Steps | 1000 |
| Return | 7031.927 |
| Mean reward | 7.032 |
| Mean x velocity | 7.465 |
| Final x position | 373.190 |
| Minimum torso height | 0.534 |
| Maximum absolute root angle | 0.269 |
| Fell | false |
Load
from stable_baselines3 import SAC
model = SAC.load("sac_half_cheetah.zip")
Use the included wrapper for matching evaluation.
from sac_cheetah.config import TrainConfig
from sac_cheetah.envs import make_env
cfg = TrainConfig()
env = make_env(cfg.env_id, cfg.seed + 1, render_mode="rgb_array")
- Task
- Reinforcement Learning
- Library
- stable-baselines3
- Created
- Jun 26, 2026
- Updated
- Jun 26, 2026