Stars
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.
Command-line fetch tools for system/other information
Hydra is a framework for elegantly configuring complex applications
A markdown version emoji cheat sheet
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
FinRL®: Financial Reinforcement Learning. 🔥
Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.
Python sample codes and textbook for robotics algorithms.
A Best-of-list of Robot Simulators, re-generated weekly on Wednesdays
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
jekyll extensions for the blogging scholar
This is the code repository for IntPhys 2, a video benchmark designed to evaluate the intuitive physics understanding of deep learning models.
Mobile manipulation research tools for roboticists
Library to compare and evaluate reward functions
A community-maintained Python framework for creating mathematical animations.
Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch
Gym environment for cooperative multi-agent reinforcement learning in heterogeneous robot teams
A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.
Pympress is a simple yet powerful PDF reader designed for dual-screen presentations
Isaac Gym Environments for Legged Robots
An elegant PyTorch deep reinforcement learning library.
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
Tools for accelerating safe exploration research.
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
S3D Text-Video model trained on HowTo100M using MIL-NCE