Update RL Model: Add/Update model 'PPO-CartPole-v1-ep106' and regenerate unified README.md
62f3bdb verified metadata
library_name: stable-baselines3
tags:
- reinforcement-learning
- deep-reinforcement-learning
- agenlus
Agenlus Model Hub 🚀
Welcome to your Agenlus Reinforcement Learning repository! This repository hosts multiple trained models.
📊 Models Summary
| Model Name | Environment | Algorithm | Best Score | Episodes | Links |
|---|---|---|---|---|---|
| PPO-CartPole-v1-ep106 | CartPole-v1 |
PPO |
55.94 | 106 | Browse Files |
📝 Model Details & Instructions
📦 PPO-CartPole-v1-ep106
- Environment:
CartPole-v1 - RL Algorithm:
PPO - Best Avg Reward:
55.94 - Episodes Trained:
106
Description: PPO model trained on CartPole-v1 for 106 episodes. Best avg reward: 55.94.
How to load:
const model = await tf.loadLayersModel('https://huggingface.co/umjunsik1323/RL_Models/raw/main/PPO-CartPole-v1-ep106/model.json');