You can deploy this model and start earning money today!

fschnell/
q_learning_FrozenLake-v1

Name: q_learning_FrozenLake-v1
Availability: InStock

FrozenLake-v1

q-learning

reinforcement-learning

custom-implementation

model-index

Views

No views yet

Q-Learning Agent playing FrozenLake-v1

This is a trained Q-Learning agent for FrozenLake-v1.

Evaluation

Mean reward: 0.72 +/- 0.45
Number of evaluation episodes: 100
is_slippery: True

Usage

python

import pickle
import gymnasium as gym
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="fschnell/q_learning_FrozenLake-v1", filename="q-learning.pkl")
with open(model_path, "rb") as f:
    model = pickle.load(f)

env = gym.make(
    model["env_id"],
    is_slippery=model.get("is_slippery", True),
    render_mode="rgb_array",
)
q_table = model["qtable"]