xiaomengy

xiaomengy's Stars

• pytorch/pytorch

  Tensors and Dynamic neural networks in Python with strong GPU acceleration

  Language:Python83.5k1.7k46.1k22.5k

• electronicarts/CnC_Remastered_Collection

  Language:C++18.3k524994.7k

• facebookarchive/caffe2

  Caffe2 is a lightweight, modular, and scalable deep learning framework.

  Language:Shell8.4k5281.3k1.9k

• facebookresearch/mae

  PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

  Language:Python7.3k561921.2k

• google-deepmind/alphageometry

  Language:Python4.1k53122465

• google-deepmind/mctx

  Monte Carlo tree search in JAX

  Language:Python2.3k2848190

• pytorch/rl

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

  Language:Python2.3k41629305

• google/coding-competitions-archive

  Google Coding Competitions problem archive

  Language:HTML975313265

• facebookresearch/nle

  The NetHack Learning Environment

  Language:C94030113113

• NVlabs/curobo

  CUDA Accelerated Robot Library

  Language:Python77417196120

• google-deepmind/reverb

  Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

  Language:C++7022512493

• XuezheMax/megalodon

  Reference implementation of Megalodon 7B model

  Language:Cuda50414752

• pytorch-labs/LeanRL

  LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

  Language:Python4208717

• google-deepmind/alphastar

  Language:Python40911652

• facebookresearch/moolib

  A library for distributed ML training with PyTorch

  Language:C++366121920

• facebookresearch/nocturne

  A data-driven, fast driving simulator for multi-agent coordination under partial observability.

  Language:Python263134529

• MichaelTMatthews/Craftax

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

  Language:Python19731321

• sotopia-lab/sotopia

  Sotopia: an Open-ended Social Learning Environment (ICLR 2024 spotlight)

  Language:Python15927019

• adamkarvonen/chess_gpt_eval

  A repo to evaluate various LLM's chess playing abilities.

  Language:Python642715

• facebookresearch/jps

  Code for "Joint Policy Search for Collaborative Multi-agent Incomplete Information Games"

  Language:C++501028

• AntoineRichard/OmniLRS

  SpaceR and SRL Lunar simulation

  Language:Python4731313

• BricksRL/bricksrl

  BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO

  Language:Python46102