---
env_name: LunarLander-v3
tags:
- LunarLander-v3
- rainbow-dqn
- reinforcement-learning
- custom-implementation
- deep-q-learning
- pytorch
- rainbow
- dqn
model-index:
- name: Rainbow-2d-LunarLander-v3
  results:
  - task:
      type: reinforcement-learning
      name: reinforcement-learning
    dataset:
      name: LunarLander-v3
      type: LunarLander-v3
    metrics:
    - type: mean_reward
      value: 192.34 +/- 127.62
      name: mean_reward
      verified: false
---

# **Rainbow-DQN** Agent playing **LunarLander-v3**
This is a trained model of a **Rainbow-DQN** agent playing **LunarLander-v3**.

## Usage
### create the conda env in https://github.com/GeneHit/drl_practice
```bash
conda create -n drl python=3.12
conda activate drl
python -m pip install -r requirements.txt
```

### play with full model
```python
# load the full model
model = load_from_hub(repo_id="winkin119/Rainbow-2d-LunarLander-v3", filename="full_model.pt")

# Create the environment. Don't forget to check the necessary wrappers in the env setup.
env = gym.make("LunarLander-v3")
state, _ = env.reset()
action = model.action(state)
...
```
There is also a state dict version of the model, you can check the corresponding definition in the repo.