MattStammers/q-FrozenLake-v1-8x8-Slippery-take3

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="MattStammers/q-FrozenLake-v1-8x8-Slippery-take3", 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"])

{'env_id': 'FrozenLake-v1', 'max_steps': 200, 'n_training_episodes': 1000000, 'n_eval_episodes': 100, 'eval_seed': [], 'learning_rate': 0.2, 'gamma': 0.99, 'max_epsilon': 1, 'min_epsilon': 0.05, 'decay_rate': 0.0005}

Reduction in the learning rate and extension of training episodes seems to be producing better results. If one further attempt doesn't best this I will leave it there