README.md

metadata

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.

Usage (with Stable-baselines3)

TODO: Add your code

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  
    )