A2C Agent playing PandaReachDense-v3
This is a trained model of an A2C agent playing PandaReachDense-v3 using the stable-baselines3 library for Unit 6 of the Hugging Face Deep RL Course.
- Downloads last month
- 7
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-0.32 +/- 0.13
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="SimhaSimha/a2c-PandaReachDense-v3", filename="{MODEL FILENAME}.zip", )