Yujana/a2c-PandaReachDense-v3

A2C Agent playing PandaReachDense-v3

This is a trained model of an A2C agent playing PandaReachDense-v3 using the stable-baselines3 library and panda-gym.

Evaluation Results

• Mean Reward: -0.20 +/- 0.09
• Score (Mean - Std): -0.29 (Requirement: >= -3.5)

Usage (with Stable-baselines3)

from stable_baselines3 import A2C
from huggingface_sb3 import load_from_hub

checkpoint = load_from_hub(
    repo_id="Yujana/a2c-PandaReachDense-v3",
    filename="a2c-PandaReachDense-v3.zip",
)
model = A2C.load(checkpoint)