metadata
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-Taxi-v3-final
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 8.34 +/- 2.65
name: mean_reward
verified: true
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-final", 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"])
This was an accident but it worked - it is obviously cheating somehow but it was fully unintentional
'env_id': 'Taxi-v3', 'max_steps': 200, 'n_training_episodes': 2000000, 'n_eval_episodes': 100, 'eval_seed': [], 'learning_rate': 0.15, 'gamma': 0.99, 'max_epsilon': 1, 'min_epsilon': 0.05, 'decay_rate': 0.0005,