diditforlulz273

albumentations

Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

CORL

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

open-metric-learning

Library for metric learning pipelines and models.

ChordMixer

The official implementation of the ChordMixer architecture.

postflop-solver

[Development suspended] An efficient open-source postflop solver library written in Rust

OMPEval

Fast C++ poker hand evaluator and equity calculator

translate

A module grouping multiple translation APIs

rtdl

Research on Tabular Deep Learning: Papers & Packages

ipython-autotime

Time everything in IPython

simple-virus-scanner

PHP file scanner for known virus patterns of simple viruses for Bitrix, WordPress and Joomla

pypi_iterator

manifold

A model-agnostic visual debugging tool for machine learning

nextDoor

Next Door neighbours Python implementation

RecommenderSystems

faiss

A library for efficient similarity search and clustering of dense vectors.

contrastiveExplanation

Implicit contrastive explanations in GBDT regressors

LSTM-FCN-Ablation

Repository for the ablation study of "Long Short-Term Memory Fully Convolutional Networks for Time Series Classification"

opensoldat

OpenSoldat is a unique 2D (side-view) multiplayer action game

pytorch-forecasting

Time series forecasting with PyTorch

wog

In the Wake of Gods 3.59 alpha

Halite

Kaggle Halite RL challenge - Provisional first place solution

randomgen

Numpy-compatible bit generators and add some random variate distributions missing from NumPy.

DQN-Atari-Agents

DQN-Atari-Agents: Modularized & Parallel PyTorch implementation of several DQN Agents, i.a. DDQN, Dueling DQN, Noisy DQN, C51, Rainbow, and DRQN

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

TicTacToe-DL-RL

Implementation of Tic Tac Toe 5x5 (4 in a row). Uses a DNN together with MCTS and Neuroevolution to train the weights. The network is similar to the one used by AlphaZero but with fewer residual layers and fewer filters.

Poker-MCCFRM

A poker AI for NL Texas Holdem trained using Monte-Carlo Counterfactual Regret Minimization.

DREAM

Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games

TexasHoldemBot

DeeperStack: DeepHoldem Evil Brother

Hacksby

Description and unofficial implementation of Furby's audio protocol

PokerRL-Omaha

Omaha Poker functionality+some features for PokerRL Reinforcement Learning card framwork