README.md

metadata

tags:
  - FrozenLake-v1-4x4
  - q-learning
  - reinforcement-learning
  - custom-implementation
model-index:
  - name: q-FrozenLake-v1-custom-map-Slippery-edition
    results:
      - task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: FrozenLake-v1-4x4
          type: FrozenLake-v1-4x4
        metrics:
          - type: mean_reward
            value: 0.89 +/- 0.31
            name: mean_reward
            verified: false

Q-Learning Agent playing1 FrozenLake-v1

This is a trained model of a Q-Learning agent playing FrozenLake-v1 .

Usage

model = load_from_hub(repo_id="kinkpunk/q-FrozenLake-v1-custom-map-Slippery-edition",
                      filename="q-learning.pkl")

# Don't forget to change additional attributes
# when you create environment using 4x4 map
env = gym.make('FrozenLake-v1',
                desc=["SFFF", "FHHF", "FFHF", "HFFG"],
                is_slippery=True)