panda-gym: Open-source goal-conditioned environments for robotic learning
Paper • 2106.13687 • Published • 3
A2C Agent playing PandaReachDense-v2
This is a trained model of a A2C agent playing PandaReachDense-v2 using the stable-baselines3 library.
https://huggingface.co/papers/2106.13687
...
- Downloads last month
- 4
Paper for mgmeskill/a2c-PandaReachDense-v2
Evaluation results
- mean_reward on PandaReachDense-v2self-reported-5.42 +/- 0.86
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="mgmeskill/a2c-PandaReachDense-v2", filename="{MODEL FILENAME}.zip", )