Stars
Claude Code & Codex skills that build complete Godot projects from a game description
Native and Compact Structured Latents for 3D Generation
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
Typed argument parser for Python
VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Library to compare and evaluate reward functions
JAX (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
Real-time stock tickers from the command-line.
Official PyTorch Implementation of Proxy Anchor Loss for Deep Metric Learning, CVPR 2020
PyTorch package for the discrete VAE used for DALL·E.
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
A course in reinforcement learning in the wild
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
Supplementary code for the paper "Hyperbolic Image Embeddings".
The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …
A library of reinforcement learning components and agents
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
Hydra is a framework for elegantly configuring complex applications