Stars
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
All course materials for the Zero to Mastery Deep Learning with TensorFlow course.
A curated list of awesome healthcare taxonomies and knowledge graphs.
A curated list of reinforcement learning with human feedback resources (continually updated)
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…
[ICLR 2023 spotlight] MEDFAIR: Benchmarking Fairness for Medical Imaging
Implementation of TACL 2017 paper: Cross-Sentence N-ary Relation Extraction with Graph LSTMs. Nanyun Peng, Hoifung Poon, Chris Quirk, Kristina Toutanova and Wen-tau Yih.
The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
Open-source simulator for autonomous driving research.
Kojoley / atari-py
Forked from openai/atari-pyAn `openai/atari-py` fork with Windows support and removed zlib/libpng dependencies. Binaries (wheels) are on "Releases" tab.
Attention based model for learning to solve different routing problems
Some notes on things I find interesting and important.
Open source code for paper "Denoised MDPs: Learning World Models Better Than the World Itself"
Denoising Diffusion Probabilistic Models
A pytorch implementation of the vector quantized variational autoencoder (https://arxiv.org/abs/1711.00937)
Perform data science on data that remains in someone else's server
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"
R-GAP: Recursive Gradient Attack on Privacy [Accepted at ICLR 2021]
Multi-Joint dynamics with Contact. A general purpose physics simulator.