A2C Agent playing PandaReachDense-v2
This is a trained model of a A2C agent playing PandaReachDense-v2 using the stable-baselines3 library.
Hyperparameters
# 4
policy = "MultiInputPolicy"
learning_rate=0.001
gamma=0.95
time_steps=100000
...
- Downloads last month
- -
Evaluation results
- mean_reward on PandaReachDense-v2self-reported-0.99 +/- 0.20
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="ahmad-alismail/a2c-PandaReachDense-v2", filename="{MODEL FILENAME}.zip", )