Skip to content

Commit 837ed22

Browse files
committed
Add changes to publish.yml and README.md
1 parent d35d111 commit 837ed22

File tree

2 files changed

+18
-9
lines changed

2 files changed

+18
-9
lines changed

.github/workflows/publish.yml

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -58,6 +58,8 @@ jobs:
5858
name: Create GitHub Release 🏷️
5959
needs: publish-to-pypi
6060
runs-on: ubuntu-latest
61+
# permissions:
62+
# contents: write
6163
steps:
6264
- name: Download built distributions
6365
uses: actions/download-artifact@v4

README.md

Lines changed: 16 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,22 @@
11
# 🚀 OptimRL: Group Relative Policy Optimization
22

3+
34
OptimRL is a **high-performance reinforcement learning library** that introduces a groundbreaking algorithm, **Group Relative Policy Optimization (GRPO)**. Designed to streamline the training of RL agents, GRPO eliminates the need for a critic network while ensuring robust performance with **group-based advantage estimation** and **KL regularization**. Whether you're building an AI to play games, optimize logistics, or manage resources, OptimRL provides **state-of-the-art efficiency and stability**.
45

5-
---
6+
## 🏅 Badges
7+
8+
![PyPI Version](https://img.shields.io/pypi/v/optimrl)
9+
![PyPI Downloads](https://img.shields.io/pypi/dm/optimrl)
10+
![Python Version](https://img.shields.io/pypi/pyversions/optimrl)
11+
![Python](https://img.shields.io/badge/Python-3.8%2B-blue?logo=python&logoColor=white)
12+
![C](https://img.shields.io/badge/C-99-00599C?logo=c&logoColor=white)
13+
![NumPy](https://img.shields.io/badge/Library-NumPy-013243?logo=numpy&logoColor=white)
14+
![PyTorch](https://img.shields.io/badge/Framework-PyTorch-EE4C2C?logo=pytorch&logoColor=white)
15+
![Setuptools](https://img.shields.io/badge/Tool-Setuptools-3776AB?logo=python&logoColor=white)
16+
![Build Status](https://github.com/subaashnair/optimrl/actions/workflows/tests.yml/badge.svg)
17+
![CI](https://github.com/subaashnair/optimrl/workflows/CI/badge.svg)
18+
![Coverage](https://img.shields.io/codecov/c/github/subaashnair/optimrl)
19+
![License](https://img.shields.io/github/license/subaashnair/optimrl)
620

721
## 🌟 Features
822

@@ -172,17 +186,10 @@ If you use OptimRL in your research, please cite:
172186
title={OptimRL: Group Relative Policy Optimization},
173187
author={Your Name},
174188
year={2024},
175-
url={https://github.com/yourusername/optimrl}
189+
url={https://github.com/subaashnair/optimrl}
176190
}
177191
```
178192

179193
---
180194

181-
## 🏅 Badges
182195

183-
![PyPI Version](https://img.shields.io/pypi/v/optimrl)
184-
![PyPI Downloads](https://img.shields.io/pypi/dm/optimrl)
185-
![Python Version](https://img.shields.io/pypi/pyversions/optimrl)
186-
![Build Status](https://github.com/yourusername/optimrl/actions/workflows/tests.yml/badge.svg)
187-
![Coverage](https://img.shields.io/codecov/c/github/yourusername/optimrl)
188-
![License](https://img.shields.io/github/license/yourusername/optimrl)

0 commit comments

Comments
 (0)