README.md

metadata

tags:
  - FrozenLake-v1-8x8
  - q-learning
  - reinforcement-learning
  - custom-implementation
  - Lucas_is_the_best
model-index:
  - name: q-FrozenLake-v1-8x8-Slipper
    results:
      - metrics:
          - type: mean_reward
            value: 0.38 +/- 0.49
            name: mean_reward
        task:
          type: reinforcement-learning
          name: reinforcement-learning
        dataset:
          name: FrozenLake-v1-8x8
          type: FrozenLake-v1-8x8

Q-Learning Agent playing1

This is a trained model of a Q-Learning agent playing

Usage

model = load_from_hub(repo_id="lucasbertola/q-FrozenLake-v1-8x8-Slipper", filename="q-learning.pkl")

# Don't forget to check if you need to add additional attributes (is_slippery=True etc)
env = gym.make(model["env_id"])