Q-Learning Agent playing Grid3D-v0
This is a trained model of a Q-Learning agent playing Grid3D-v0 .
Usage
model = load_from_hub(repo_id="hassan2k2/q-Grid3D-v0", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=True etc)
# For Grid3D-v0, first download grid3d.py from this repo and run: import grid3d
env = gym.make(model["env_id"])
Evaluation results
- mean_reward on Grid3D-v0self-reported-0.83 +/- 1.14