Stars
Code for our ICLR 2024 paper "Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning".
Hopefully this will be a stable, helpful, open source of validated guidance, navigation, dynamics, and control code functionality, all written in Python.
Helper application for Linux distributions serving as a kind of "entry point" for running and integrating AppImages
A port of ParrotSec's stealth and anonsurf modules to Kali Linux
Matplotlib styles for scientific plotting
HIPPO 🦛 is an explainable AI method and toolkit for weakly-supervised models in computational pathology. It enables hypothesis testing on tissue and searching for high-effect and low-effect tissue …
Make Zotero effective for us LaTeX holdouts
Linux driver for Realtek RTL8111/8168/8411 PCIe GBE NIC
A Python based lightweight robot simulator for the development of algorithms in robotics navigation, control, and learning.
Conversion between Traditional and Simplified Chinese
ibus / ibus
Forked from phuang/ibusIntelligent Input Bus for Linux/Unix
CantoInput - an input method (IME) for Cantonese
Python tool for turning Chinese vocabulary into Anki-ready flashcards.
Collection of OpenAI parametrized action-space environments.
Create beautiful diagrams just by typing notation in plain text.
A Latex style and template for paper preprints (based on NIPS style)
This is the official implementation of Multi-Agent PPO (MAPPO).
FUSE filesystem over Google Drive
Multi-Agent Reinforcement Learning with Stable-Baselines3
An elegant PyTorch deep reinforcement learning library.
Pytorch implementation of PPO-Lagrangian, compared against PPO in a continous action Cart Pole environment.
Implementation of PPO Lagrangian in PyTorch
New repo collection for NVIDIA Cosmos: https://github.com/nvidia-cosmos