AIbase
Product LibraryTool Navigation

Humanoid-Robot-Reinforcement-Learning-PPO

Public

This repository contains a project that leverages reinforcement learning to make a humanoid robot walk in a PyBullet simulation. It uses a custom Gym environment, a Proximal Policy Optimization (PPO) agent, and a provided URDF file for the robot model. The training process prints rewards per generation and visualizes the robot's behavior.

Creat2024-06-24T14:59:41
Update2025-03-02T18:09:27
6
Stars
0
Stars Increase