awesome-AI-books

: A toolkit for developing and comparing reinforcement learning algorithms. (Can play with , Box2d, MuJoCo etc...)

malmo

: Project Malmö is a platform for Artificial Intelligence experimentation and research built on top of Minecraft

DeepMind Pysc2

: StarCraft II Learning Environment

Procgen

: Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

: A bot platform for machine learning research on StarCraft®: Brood War®

: Dota2 game acessing api. ( )

Mario AI Framework

: A Mario AI framework for using AI methods

Google Dopamine

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

TextWorld

: Microsoft - A learning environment sandbox for training and testing reinforcement learning (RL) agents on text-based games

Mini Grid

: Minimalistic gridworld environment for OpenAI Gym

MAgent

: A Platform for Many-agent Reinforcement Learning

XWorld

: A C++/Python simulator package for reinforcement learning

Neural MMO

: A Massively Multiagent Game Environment

MinAtar

: MinAtar is a testbed for AI agents which implements miniaturized version of several Atari 2600 games

craft-env

: CraftEnv is a 2D crafting environment

gym-sokoban

: Sokoban is Japanese for warehouse keeper and a traditional video game

Pommerman

Playground hosts Pommerman, a clone of Bomberman built for AI research

gym-miniworld

MiniWorld is a minimalistic 3D interior environment simulator for reinforcement learning & robotics research

vizdoomgym

OpenAI Gym wrapper for (A Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information) enviroments

ddz-ai

以孤立语假设和宽度优先搜索为基础，构建了一种多通道堆叠注意力Transformer结构的斗地主ai

Stuart Russell & peter Norvig

Rishal Hurbans

Sheldon M Ross

Stephen Boyd

Thomas Cover & Jay A Thomas

Kenneth H. Rosen

Gilbert Strang

David C Lay

Edwin Thompson Jaynes

Morris H. DeGroot

Roger Casella

Thomas Cover & Jay A Thomas

Stephen Boyd

陈希儒

吴军

Sheldon M Ross

David C Lay

Roger Casella

Kenneth H.Rosen

Pang-Ning Tan

Toby Segaran

Amanda Casari, Alice Zheng

Toby Segaran

David J C MacKay

Tom M. Mitchell

Christopher Bishop

Trevor Hastie

Michael Beyeler ( )

周志华

Tom M. Mitchell

李航

(Using MXNet)An interactive deep learning book with code, math, and discussions

d2l-pytorch

(Dive into Deep Learning) pytorch version

(Dive into Deep Learning) for chinese

Ian Goodfellow & Yoshua Bengio & Aaron Courville

Li Deng & Dong Yu

Yoshua Bengio

Stephen Marsland

Martin Hagan

Simon Haykin

Sandhya Samarasinghe

Ian Goodfellow & Yoshua Bengio & Aaron Courville

Simon Haykin

Martin Hagan

Ajay Thampi

Andrew R. Freed

Stuart Russell

Max Tegmark

Nick Bostrom

D-Wave quantum computing primer

Quantum computing 101, from University of Waterloo

Quantum Computation and Quantum Information - Nielsen

量子计算和量子信息（量子计算部分）- Nielsen

ProjectQ

ProjectQ is an open source effort for quantum computing

Stable Diffusion

[ ] A latent text-to-image diffusion model

Stable Diffusion V2

High-Resolution Image Synthesis with Latent Diffusion Models

GFPGAN

[ ] GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

ESRGAN

[ ] ECCV18 Workshops - Enhanced SRGAN. Champion PIRM Challenge on Perceptual Super-Resolution. The training codes are in BasicSR

CodeFormer

[ ] - [NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

UniPC

[ ] UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Google DeepMind Asynchronous Advantage Actor-Critic algorithm

SARSA - Q-Learning is a value-based Reinforcement Learning algorithm

Deep Deterministic Policy Gradient,

Large-Scale Study of Curiosity-Driven Learning

OpenAI Proximal Policy Optimization Algorithms

OpenAI Random Network Distillation, an exploration bonus for deep reinforcement learning method

OpenAI Variational Information Maximizing Exploration

Deep Quality-Value (DQV) Learning

Evolution-Guided Policy Gradient in Reinforcement Learning

Mean Field Multi-Agent Reinforcement Learning. (this paper include MF-Q and MF-AC)

Actor-Attention-Critic for Multi-Agent Reinforcement Learning

A collection of feature selection algorithms, available on

( ) - Machine Learning in Python

Linfa

( ) - spirit of , a rust ML lib

( ) - Xgboost lib's document

( ) - Microsoft lightGBM lib's features document

( ) - Yandex Catboost lib's key algorithm pdf papper

StackNet

( ) - Some model stacking algorithms implemented in this lib

Learning Nonlinear Functions Using (multi-core implementation )

, , , - Factorization Machines and some extended Algorithms

GNN Papers

Must-read papers on graph neural networks (GNN)

Rethinking Model Scaling for Convolutional Neural Networks

Densely Connected Convolutional Networks

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Pre-training of Deep Bidirectional Transformers for Language Understanding

Language Models are Few-Shot Learners

Fast Region-based Convolutional Network method (Fast R-CNN) for object detection

Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition

DeepMind Generative Query Network, Neural scene representation and rendering

Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs

Model Search

( ) - Google Model search (MS) is a framework that implements AutoML algorithms for model architecture search at scale

TPOT

( ) - TPOT is a lib for AutoML

( ) - auto-sklearn is an automated machine learning toolkit and a drop-in replacement for a scikit-learn estimator

( ) - Auto-Keras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab

( ) - TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library written in Scala that runs on top of Spark

Provides automatic selection of models and hyperparameters for

MLBox

( ) - MLBox is a powerful Automated Machine Learning python library

ZenML

( ) - ZenML is built for ML practitioners who are ramping up their ML workflows towards production

( ) - T-distributed Stochastic Neighbor Embedding (t-SNE) is a machine learning algorithm for visualization

( ) - Principal component analysis

( ) - Linear Discriminant Analysis

( ) - Locally linear embedding

Laplacian Eigenmaps for Dimensionality Reduction and Data Representation

( ) - Sammon mapping is designed to minimise the differences between corresponding inter-point distances in the two spaces

Pandas

( ) - Flexible and powerful data analysis / manipulation library for Python

Polars

( ) - Lightning-fast DataFrame library for Rust and Python

Horovod

Horovod is a distributed training framework for TensorFlow, Keras, PyTorch, and MXNet. The goal of Horovod is to make distributed Deep Learning fast and easy to use

Acme

A Research Framework for (Distributed) Reinforcement Learning

bagua

Bagua is a flexible and performant distributed training algorithm development framework