A2C Agent playing PandaReachDense-v3
This is a trained model of an A2C agent playing PandaReachDense-v3 using Stable-Baselines3 and VecNormalize.
Evaluation Results
Mean Reward: -1.50 +/- 0.30 (Required for pass: >= -3.5)
Usage
from stable_baselines3 import A2C
from huggingface_sb3 import load_from_hub
model = load_from_hub(repo_id="Ravikanth8788/a2c-PandaReachDense-v3", filename="a2c-PandaReachDense-v3.zip")
- Downloads last month
- 11
Evaluation results
- mean_reward on PandaReachDense-v3self-reported-1.50 +/- 0.30