dhyuti-n/autorl-sac-halfcheetah-v5-20260607-210320
03
SAC on HalfCheetah-v5
Trained automatically by [AutoRL](https://github.com/wandb/autorl) — a multi-agent RL training race powered by W&B, Weave, and OpenAI.
Performance
Usage
# pip install stable-baselines3 huggingface_hub gymnasium mujoco imageio
from huggingface_hub import hf_hub_download
from stable_baselines3 import SAC
import gymnasium as gym
import imageio
# Load the winning model from HuggingFace
model_path = hf_hub_download(repo_id="dhyuti-n/autorl-sac-halfcheetah-v5-20260607-210320", filename="model.zip")
model = SAC.load(model_path)
# Record a video rollout
env = gym.make("HalfCheetah-v5", render_mode="rgb_array")
obs, _ = env.reset(seed=0)
frames, done = [], False
while not done:
frames.append(env.render())
action, _ = model.predict(obs, deterministic=True)
obs, _, terminated, truncated, _ = env.step(action)
done = terminated or truncated
env.close()
imageio.mimsave("rollout.mp4", frames, fps=30)
print("✓ Saved rollout.mp4")