|
--- |
|
library_name: stable-baselines3 |
|
tags: |
|
- LunarLander-v2 |
|
- deep-reinforcement-learning |
|
- reinforcement-learning |
|
- stable-baselines3 |
|
model-index: |
|
- name: DQN |
|
results: |
|
- task: |
|
type: reinforcement-learning |
|
name: reinforcement-learning |
|
dataset: |
|
name: LunarLander-v2 |
|
type: LunarLander-v2 |
|
metrics: |
|
- type: mean_reward |
|
value: 241.60 +/- 48.03 |
|
name: mean_reward |
|
verified: false |
|
--- |
|
|
|
# **DQN** Agent playing **LunarLander-v2** |
|
This is a trained model of a **DQN** agent playing **LunarLander-v2** |
|
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). |
|
|
|
## Usage (with Stable-baselines3) |
|
TODO: Add your code |
|
|
|
|
|
```python |
|
from stable_baselines3 import ... |
|
from huggingface_sb3 import load_from_hub |
|
|
|
#The hyper-parameter |
|
model = DQN( |
|
"MlpPolicy", |
|
env=env, |
|
buffer_size=100000, |
|
learning_starts=50000, |
|
batch_size=128, |
|
train_freq=1, |
|
gradient_steps=3, |
|
tau=1.0, |
|
gamma=0.99, |
|
learning_rate=0.0001, |
|
target_update_interval=10000, |
|
exploration_initial_eps=1.0, |
|
exploration_fraction=0.1, |
|
exploration_final_eps=0.05, |
|
policy_kwargs=dict(net_arch=[256, 256]), |
|
device='auto', |
|
verbose=1 |
|
) |
|
|
|
|
|
|