|
--- |
|
tags: |
|
- FrozenLake-v1-4x4 |
|
- q-learning |
|
- reinforcement-learning |
|
- custom-implementation |
|
model-index: |
|
- name: frozenLake_4x4_nonSlippery |
|
results: |
|
- metrics: |
|
- type: mean_reward |
|
value: 0.79 +/- 0.41 |
|
name: mean_reward |
|
task: |
|
type: reinforcement-learning |
|
name: reinforcement-learning |
|
dataset: |
|
name: FrozenLake-v1-4x4 |
|
type: FrozenLake-v1-4x4 |
|
--- |
|
|
|
# **Q-Learning** Agent playing **FrozenLake-version-1** |
|
This is a trained model of a **Q-Learning Algorithm** agent playing in the **FrozenLake-v1 Environment** . |
|
|
|
## Usage |
|
```python |
|
model = load_from_hub(repo_id="iiShreya/frozenLake_4x4_nonSlippery", filename="q-learning.pkl") |
|
env = gym.make(model["env_id"]) |
|
evaluate_agent(env, model["max_steps"], model["n_eval_episodes"], model["qtable"], model["eval_seed"]) |
|
|
|
``` |
|
|
