PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

A fork of OpenAI Baselines, implementations of reinforcement learning algorithms

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

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

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

Clean PyTorch implementations of imitation and reward learning algorithms

PFRL: a PyTorch-based deep reinforcement learning library

High throughput synchronous and asynchronous reinforcement learning

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

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

Benchmarking the Spectrum of Agent Capabilities

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

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

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

Baba Is You simulator using C++ with some reinforcement learning

Starter kit for getting started in the Music Demixing Challenge.

"Age of Empires II" Learning Environment

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

Code to reproduce Neural Game Engine experiments and pre-trained models

Standard interface for entity based reinforcement learning environments.

Reinforcement learning with RealAnt: an open-source low-cost quadruped

Behavioural cloning experiments with video games

StarCraft 2 Imitation Learning

An AI for the game Super Hexagon based on reinforcement learning

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

Creating fixed-length vectors to describe RL/GA policies