timoklein

rejax

pgx

♟️ Vectorized RL game environments in JAX

flax

Flax is a neural network library for JAX that is designed for flexibility.

ruff-action

A GitHub Action for Ruff

distreqx

Distrax, but in equinox. Lightweight JAX library of probability distributions and bijectors.

Stoix

🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL

get-started-with-JAX

The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well as the content I found useful while learning about the JAX ecosystem.

DrM

DrM, a visual RL algorithm, minimizes the dormant ratio to guide exploration-exploitation trade-offs, achieving significant improvements in sample efficiency and asymptotic performance across diverse domains.

dopamine

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

redo

ReDo: The Dormant Neuron Phenomenon in Deep Reinforcement Learning (pytorch)

CrossQ

Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"

beartype

Unbearably fast near-real-time hybrid runtime-static type-checking in pure Python.

torchtyping

Type annotations and dynamic checking for a tensor's shape, dtype, names, etc.

jaxonloader

A dataloader, but for JAX

Craftax

(Crafter + NetHack) in JAX. ICML 2024 Spotlight.

equinox

Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

torchbeast

A PyTorch Platform for Distributed RL

professional-programming

A collection of learning resources for curious software engineers

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

einx

Universal Tensor Operations in Einstein-Inspired Notation for Python.

Warp

Warp is a modern, Rust-based terminal with AI built in so you and your team can build great software, faster.

BunDLe-Net

Behavioural and Dynamic Learning Network (BunDLe-Net) is an algorithm to learn meaningful coarse-grained representations from time-series data. It maps high-dimensional data to low-dimensional space while preserving both dynamical and behavioural information. It has been applied, but is not limited to neuronal manifold learning.

backpack

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

FriendsDontLetFriends

Friends don't let friends make certain types of data visualization - What are they and why are they bad.

flashbax

⚡ Flashbax: Accelerated Replay Buffers in JAX

TACO

Code for "TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning"

d2l-en

Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.

xland-minigrid

JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

stat_rethinking_2024

haliax

Named Tensors for Legible Deep Learning in JAX