A2C Agent playing PandaReachDense-v3

This is a trained A2C agent playing PandaReachDense-v3 using the Stable-Baselines3 library.

Model

  • Algorithm: A2C
  • Environment: PandaReachDense-v3
  • Library: Stable-Baselines3
  • Task: Robotic arm reaching a target position

Usage with Stable-Baselines3

from stable_baselines3 import A2C
from huggingface_sb3 import load_from_hub

checkpoint = load_from_hub(
    repo_id="roshana1s/a2c-PandaReachDense-v3",
    filename="a2c-PandaReachDense-v3.zip"
)

model = A2C.load(checkpoint)

The trained agent learns to control the Panda robotic arm and move its end-effector toward the target position while maximizing the environment reward.

Repository

Model available on Hugging Face:

roshana1s/a2c-PandaReachDense-v3

Downloads last month
27
Video Preview
loading

Evaluation results