Q-Learning Agent playing FrozenLake-v1
This is a trained Q-Learning agent playing FrozenLake-v1.
Usage
from huggingface_hub import hf_hub_download
import pickle, gymnasium as gym
path = hf_hub_download(repo_id="macoberry/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
with open(path, "rb") as f:
model = pickle.load(f)
env = gym.make(model["env_id"])
Evaluation results
- mean_reward on FrozenLake-v1-4x4-no_slipperyself-reported1.00 +/- 0.00