LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

The NetHack Learning Environment

Easily run Python at the shell! Magical, but never mysterious.

Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

Code for the experiments done in the paper "GAN-Aimbots: Using Machine Learning for Cheating in First Person Shooters"

Reinforcement learning training framework for entity-gym environments.

Entity Gym compatible ragged batch transformer implementation.

Standard interface for entity based reinforcement learning environments.

A library for distributed ML training with PyTorch

Toribash Learning Environment

[WIP] RL agent for the SuperTuxKart game.

Collection of in-progress libraries for entity neural networks.

Reinforcement Learning environments based on the 1993 game Doom

"Age of Empires II" Learning Environment

A neural network bot for playing StarCraft II

DEPRECATED - please visit https://github.com/vwxyzjn/ppo-implementation-details

A benchmark environment for fully cooperative human-AI performance.

High-throughput simulation platform for Artificial Intelligence reseach

Train an agent to play VizDoom with multi sensory inputs. Trained using sample factory

Falken provides developers with a service that allows them to train AI that can play their games

StarCraft 2 Imitation Learning

Starter kit for getting started in the Music Demixing Challenge.

A TF2.0 implementation of RL baselines.

IEEE CoG & NeurIPS workshop paper 'Counter-Strike Deathmatch with Large-Scale Behavioural Cloning'

Mirror of Stable-Baselines: a fork of OpenAI Baselines, implementations of reinforcement learning algorithms

The source code for mastering the game of Chutes and Ladders