4.0

.github/workflows/install.yml

@@ -17,7 +17,6 @@ jobs:
         py:
           - "3.11"
           - "3.10"
-          - "3.9"
         env:
           - pip
           - conda

.gitignore

@@ -2,6 +2,10 @@
 c_*.c
 pufferlib/extensions.c
 pufferlib/puffernet.c
+logs/
+
+# Build dir
+build/
 
 # hipified cuda extensions dir [HIP/ROCM]
 pufferlib/extensions/hip/
@@ -18,6 +22,7 @@ cy_*.c
 
 # C extensions
 *.so
+*.o
 
 # Distribution / packaging
 .Python
@@ -162,3 +167,8 @@ pufferlib/ocean/impulse_wars/*-release/
 pufferlib/ocean/impulse_wars/debug-*/
 pufferlib/ocean/impulse_wars/release-*/
 pufferlib/ocean/impulse_wars/benchmark/
+
+# Data
+resources/drive/data/*
+resources/drive/binaries/*
+

README.md

@@ -1,16 +1,11 @@
 ![figure](https://pufferai.github.io/source/resource/header.png)
 
-[![PyPI version](https://badge.fury.io/py/pufferlib.svg)](https://badge.fury.io/py/pufferlib)
-![PyPI - Python Version](https://img.shields.io/pypi/pyversions/pufferlib)
-![Github Actions](https://github.com/PufferAI/PufferLib/actions/workflows/install.yml/badge.svg)
-[![](https://dcbadge.vercel.app/api/server/spT4huaGYV?style=plastic)](https://discord.gg/spT4huaGYV)
-[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40jsuarez5341)](https://twitter.com/jsuarez5341)
+[![Discord](https://dcbadge.vercel.app/api/server/spT4huaGYV?style=plastic)](https://discord.gg/spT4huaGYV)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40jsuarez)](https://twitter.com/jsuarez)
 
-PufferLib is the reinforcement learning library I wish existed during my PhD. It started as a compatibility layer to make working with complex environments a breeze. Now, it's a high-performance toolkit for research and industry with optimized parallel simulation, environments that run and train at 1M+ steps/second, and tons of quality of life improvements for practitioners. All our tools are free and open source. We also offer priority service for companies, startups, and labs!
+PufferLib is a fast and sane reinforcement learning library that can train tiny, super-human models in seconds. The included learning algorithm, hyperparameter tuning, and simulation methods are the product of our own research. All our tools are free and open source. Need a high performance environment for your application? We build them professionally and offer training + extended support. Contact jsuarez🐡puffer🐡ai.
 
-![Trailer](https://github.com/PufferAI/puffer.ai/blob/main/docs/assets/puffer_2.gif?raw=true)
-
-All of our documentation is hosted at [puffer.ai](https://puffer.ai "PufferLib Documentation"). @jsuarez5341 on [Discord](https://discord.gg/puffer) for support -- post here before opening issues. We're always looking for new contributors, too!
+All of our documentation is hosted at [puffer.ai](https://puffer.ai "PufferLib Documentation"). @jsuarez5341 on [Discord](https://discord.gg/puffer) for support. Post there before opening issues. We're always looking for new contributors!
 
 ## Star to puff up the project!