aicarras

aicarras's Stars

• pytorch/pytorch

  Tensors and Dynamic neural networks in Python with strong GPU acceleration

  Language:Python82.6k1.7k45.4k22.2k

• labmlai/annotated_deep_learning_paper_implementations

  🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

  Language:Python54.4k4481325.6k

• LAION-AI/Open-Assistant

  OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

  Language:Python37k4281.6k3.2k

• ray-project/ray

  Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

  Language:Python33.3k47518.5k5.6k

• spotify/annoy

  Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

  Language:C++13.1k3183981.2k

• AI4Finance-Foundation/FinRL

  FinRL: Financial Reinforcement Learning. 🔥

  Language:Jupyter Notebook9.7k2017132.4k

• sensity-ai/dot

  The Deepfake Offensive Toolkit

  Language:Python4.1k4790401

• pytorch/rl

  A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

  Language:Python2.2k40608295

• nikhilbarhate99/PPO-PyTorch

  Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

  Language:Python1.7k961343

• AI4Finance-Foundation/FinRL-Meta

  FinRL­-Meta: Dynamic datasets and market environments for FinRL.

  Language:Python1.3k47126582

• TianhongDai/reinforcement-learning-algorithms

  This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)

  Language:Python6631510109

• sacmehta/EdgeNets

  This repository contains the source code of our work on designing efficient CNNs for computer vision

  Language:Python413193782

• ai4co/rl4co

  A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)

  Language:Python39988172

• phelber/EuroSAT

  EuroSAT: Land Use and Land Cover Classification with Sentinel-2

  396131085

• eugenevinitsky/sequential_social_dilemma_games

  Repo for reproduction of sequential social dilemmas

  Language:Python38515128132

• oceanprotocol/ocean.py

  🦑 Ocean Protocol's Python library to privately & securely publish, exchange, and consume data.

  Language:Python1701964279

• Breakend/DeepReinforcementLearningThatMatters

  Accompanying code for "Deep Reinforcement Learning that Matters"

  Language:Python15311026

• amitness/open-in-overleaf

  Access latex source of any arxiv.org paper directly on overleaf

  Language:JavaScript1462169

• cselab/smarties

  Lightweight and scalable framework for Reinforcement Learning

  Language:C++117121150

• MadryLab/implementation-matters

  Language:Python1147511

• gereleth/jupyter-bbox-widget

  A Jupyter widget for annotating images with bounding boxes

  Language:Svelte11252719

• rraileanu/auto-drac

  Automatic Data-Regularized Actor-Critic (Auto-DrAC)

  Language:Python1016518

• ashedwards/ILPO

  Official implementation of ICML paper Imitating Latent Policies from Observation

  Language:Python739121

• cselab/MARL_LES

  Repository for data and scripts of "Automating Turbulence Modeling by Multi-Agent Reinforcement Learning"

  Language:Python276121

• AdityaLab/GradABM

  [AAMAS 2023] Differentiable Agent-based Epidemiology

  Language:Python153

• ishu3101/open-with-overleaf

  A Google Chrome extension to open/edit latex files online using www.overleaf.com without the need of any software to be installed.

  Language:JavaScript104210

• jgarciab/workshop_data_viz

  Data visualization workshop (Ams data science center, 2022Feb)

  Language:Jupyter Notebook8201

• arabyalhomsi/the-software-engineer-showcaser

  A modern but simple app that enables software engineers to showcase their skills and experience.

  Language:TypeScript5102

• tobinsouth/ProcessEntropy

  A toolkit for calculating process entropy quickly. With specific applications to tweets.

  Language:Python5205

• theodi/data-ecosystems-net-zero

  The data ecosystems & innovation programme: data used to measure net zero in the UK.

  Language:Jupyter Notebook2401