Stars
All Algorithms implemented in Python
Rich is a Python library for rich text and beautiful formatting in the terminal.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
A library of reinforcement learning components and agents
OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC
Simple and reliable optimization with local, global, population-based and sequential techniques in numerical discrete search spaces.
Rap song writing recurrent neural network trained on Kanye West's entire discography
ML Collections is a library of Python Collections designed for ML use cases.
A visual programing environment for scientific computing with python
An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.
SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms
A Bunch is a Python dictionary that provides attribute-style access (a la JavaScript objects).
Differentiable controlled differential equation solvers for PyTorch with GPU support and memory-efficient adjoint backpropagation.
delete slack messages and files. An improved version is at:
BLOCK (AAAI 2019), with a multimodal fusion library for deep learning models
Solve automatic numerical differentiation problems in one or more variables.
High-performance quantum systems simulation with JAX (GPU-accelerated & differentiable solvers).
PyTorch implementation of DreamerV2 model-based RL algorithm
Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)
A simple and easy-to-use implementation of a Genetic Algorithm library in Python