Aquagym
Collection
A collection of reinforcement learning models for Gymnasium environments (see more: https://github.com/coding-kelps/aquagym).
•
8 items
•
Updated
Q-Learning Agent playing FrozenLake-v1
This is a trained model of a Q-Learning agent playing to the Gymnasium FrozenLake-v1 reinforcement learning environment.
Usage
model = load_from_hub(repo_id="coding-kelps/q-frozen-lake-v1-4x4-no-slippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
References
You can find the original source code of the model training in the corresponding Coding Kelps aquaqym repository.
Collection including coding-kelps/q-frozen-lake-v1-4x4-no-slippery
Evaluation results
- mean_reward on FrozenLake-v1-4x4-no_slipperyself-reported1.00 +/- 0.00