# nikhilbarhate99/PPO-PyTorch

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

Repository: https://github.com/nikhilbarhate99/PPO-PyTorch
Canonical: https://ross.abutalabs.com/products/ppo-pytorch
Language: Python
License: MIT
License Family: permissive
Topics: pytorch-implmention, pytorch, pytorch-tutorial, proximal-policy-optimization, reinforcement-learning-algorithms, deep-reinforcement-learning, ppo, policy-gradient, ppo-pytorch, deep-learning, reinforcement-learning
Last push: 2024-07-09T21:11:04+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2897, "days_push": 785, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2375, forks 424 (observed 2026-08-28T04:06:42.034938+00:00)

## What it is
A minimal, single-threaded PyTorch implementation of Proximal Policy Optimization (PPO) with clipped objective for OpenAI gym environments. It is designed primarily as an educational resource for beginners learning reinforcement learning, with training, testing, plotting, and GIF-making utilities.

## Use cases
- learn how the PPO reinforcement learning algorithm works
- train a PPO agent on OpenAI gym environments
- understand a minimal policy gradient implementation in PyTorch
- test pretrained PPO policies and generate gifs of agent behavior
- plot training reward curves from csv logs
- run reinforcement learning experiments in Google Colab

## When to choose
- you are a beginner wanting readable, minimal PPO code to study
- you need a simple baseline PPO implementation for standard gym environments
- you want a Colab notebook to experiment with PPO without local setup

## When to avoid
- you need a production-grade, highly optimized PPO with parallel workers and GAE
- you require state-of-the-art PPO implementation details for complex environments
- you need a maintained library with an API rather than a reference codebase

## Facets
- artifact type: learning-resource
- maturity: stable
- function: machine-learning, reinforcement-learning, deep-learning
- domain: reinforcement-learning, machine-learning, tutorials
- platform: python, cross-platform
- tags: ppo, pytorch, policy-gradient, openai-gym, educational, minimal-implementation

## Member repositories
- nikhilbarhate99/PPO-PyTorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:42.034938+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:35:03.662417+00:00, confidence not recorded.
  - readme: https://github.com/nikhilbarhate99/PPO-PyTorch (fetched 2026-08-28T04:06:42.034938+00:00, sha fe73ec2e43c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.