metadata
license: mpl-2.0
tags:
- reinforcement-learning
- stable-baselines3
- halfcheetah
- mujoco
- sb3
- sac
- control
model-index:
- name: HalfCheetah-v5-SAC
results:
- task:
type: reinforcement-learning
name: Reinforcement Learning
dataset:
name: HalfCheetah-v5
type: gymnasium
metrics:
- type: mean_reward
value: 14170.55 +/- 137.28
SAC Agent for HalfCheetah-v5
This is a Soft Actor Critic (SAC) agent trained on the HalfCheetah-v5 environment using Stable Baselines 3.
Hyperparameters
See config.json for details.
Requirements
- Python: 3.10
Dependencies
gymnasium==1.0.0
gymnasium[mujoco]
torch==2.4.0
stable_baselines3==2.4.1
How to Load
from huggingface_hub import hf_hub_download
from stable_baselines3 import SAC
model_path = hf_hub_download(repo_id="lucasschott/HalfCheetah-v5-SAC", filename="model.zip")
agent = SAC.load(model_path)