nikhilbarhate99/PPO-PyTorch

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

50
/ 100
Established

This project helps reinforcement learning practitioners train AI agents for simulated environments like those found in OpenAI Gym. It takes environment observations and desired reward signals, then outputs a trained agent that can perform actions to maximize rewards, along with performance logs and visualizations. It is designed for researchers and students learning or implementing the Proximal Policy Optimization (PPO) algorithm.

2,320 stars. No commits in the last 6 months.

Use this if you are a researcher or student looking for a straightforward PyTorch implementation of the PPO algorithm to train AI agents in simulation environments.

Not ideal if you need a production-ready, highly optimized, or multi-threaded PPO implementation for complex, real-world control systems.

reinforcement-learning AI-agent-training simulated-environments policy-optimization robotics-simulation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,320

Forks

421

Language

Python

License

MIT

Last pushed

Jul 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nikhilbarhate99/PPO-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.