Skip to content

Latest commit

 

History

62 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RocketLearn Native

C++20/Rust Rocket League RL trainer built around RocketSim and LibTorch.

The main baseline here is normal Soccar 2v2 self-play with PPO/GAE. It has batched inference, checkpoint resume/versioning, old-policy sampling and a separate evaluator.

Clone

git clone --recurse-submodules https://github.com/Speedstu/RocketLearnNative.git
cd RocketLearnNative

Already cloned without submodules:

git submodule update --init --recursive

Train

BUILD.bat
START_TRAINING.bat

Evaluate

BUILD_EVALUATOR.bat
START_EVALUATOR.bat

rocket_learn_native is the trainer and rocket_learn_evaluator is the deterministic 2v2 evaluator. There is also a small Rust supervisor for restart/log handling.

Most experiment-specific launchers live next to the main scripts. They are there because I use this repo as a working training tree, not as a polished library.

About

High-performance native C++/Rust Rocket League reinforcement learning with my shitty heatseeker profil and my kuxir current setup

Topics

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages