- London, UK
Stars
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
hill-a / stable-baselines
Forked from openai/baselinesA 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.
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
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