1
2model = load_from_hub(repo_id="MattStammers/q-FrozenLake-v1-8x8-Slippery-take3", filename="q-learning.pkl")
3
4# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
5env = 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
