Reinforcement Learning
stable-baselines3
PandaReachDense-v3
custom-implementation
Eval Results (legacy)
Instructions to use maurorisonho/a2c-PandaReachDense-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- stable-baselines3
How to use maurorisonho/a2c-PandaReachDense-v3 with stable-baselines3:
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="maurorisonho/a2c-PandaReachDense-v3", filename="{MODEL FILENAME}.zip", ) - Notebooks
- Google Colab
- Kaggle
A2C Agent for Franka Emika Panda Robotic Arm (PandaReachDense-v3)
This model is a trained Advantage Actor-Critic (A2C) agent controlling a simulated 7-DoF Franka Emika Panda robotic arm in PandaReachDense-v3, submitted for the Hugging Face Deep Reinforcement Learning Course (Unit 6).
🚀 Model Details
- Environment:
panda-gymPandaReachDense-v3 - Algorithm: Synchronous Advantage Actor-Critic (A2C) with VecNormalize
- Mean Reward: -2.0 (Passing score: >= -3.5)
- Status: Officially Verified & Certified
- Downloads last month
- 24
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-2.0 +/- 0.5