---
tags:
- CartPole-v1
- q-learning
- reinforcement-learning
- custom-implementation
metrics:
  mean_reward: 113.60 +/- 9.94
dataset:
  name: CartPole-v1
  type: gymnasium
license: mit
downloads:
  count: 0
  count_query_files:
  - config.json
  - model_index.json
  - pytorch_model.bin
  - safetensors
---

    # **DQN** Agent playing **CartPole-v1**
    This is a trained model of a **DQN** agent playing **CartPole-v1**.
    
    ## Usage
    ```python
    from stable_baselines3 import DQN
    model = DQN.load("dqn_cartpole", env=env)
    ```
    ## Training:
    model.learn(total_timesteps=300000, log_interval=250)
    
    ## Evaluation Results
    - Mean Reward: 113.60
    - Standard Deviation: 9.94