| | --- |
| | license: apache-2.0 |
| | tags: |
| | - reinforcement-learning |
| | - stable-baselines3 |
| | - ppo |
| | - gym |
| | library_name: stable-baselines3 |
| | task: reinforcement-learning |
| | --- |
| | |
| | # CartPole PPO Agent |
| |
|
| | This repository contains a **trained PPO (Proximal Policy Optimization) agent** for the **CartPole-v1** environment from OpenAI Gym. |
| | The agent is trained to balance the pole on the cart as long as possible while maximizing the reward. |
| |
|
| | --- |
| |
|
| | ## Features |
| |
|
| | - **Environment:** OpenAI Gym `CartPole-v1` |
| | - **Algorithm:** Proximal Policy Optimization (PPO) |
| | - **Trained Model:** [`ppo_cartpole.zip`](https://huggingface.co/jatinror/cartpole-ppo-agent/resolve/main/model/ppo_cartpole.zip) |
| | - **Python 3.10+ compatible** |
| | - **Direct Hugging Face Integration:** Load model for evaluation or further training |
| |
|
| | --- |
| |
|
| | ## Installation |
| |
|
| | 1. Clone the repository: |
| |
|
| | ```bash |
| | git clone https://huggingface.co/jatinror/cartpole-ppo-agent |
| | cd cartpole-ppo-agent |
| | |
| | - |
| | |
