The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

A library to generate LaTeX expression from Python code.

Democratizing Reinforcement Learning for LLMs

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

Witness the aha moment of VLM with less than $3.

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark

Official Repo for Open-Reasoner-Zero

Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

Code for "Temporal Difference Learning for Model Predictive Control"

Toolkit for vision-guided quadrupedal locomotion research

Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"

DMControl Generalization Benchmark

Video Autoencoder: self-supervised disentanglement of 3D structure and motion (ICCV 2021). Website: https://zlai0.github.io/VideoAutoencoder/

SAPIEN Manipulation Skill Benchmark (NeurIPS 2021 Track on Datasets and Benchmarks)

Robot Spin Pens

Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

MoDem Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Official repo for paper "TD-M(PC)^2: Improving Temporal Difference MPC Through Policy Constraint"

Jax/Flax Implementation of TD-MPC2

ManiSkill-Learn is a framework for training agents on SAPIEN Open-Source Manipulation Skill Challenge (ManiSkill Challenge), a physics-rich manipulation skill benchmark with large-scale demonstrati…

Finetuning Offline World Models in the Real World

Code for https://jangirrishabh.github.io/lookcloser/

The repository of ICML2023 paper: On Pre-Training for Visuo-Motor Control: Revisiting a Learning-from-Scratch Baseline

Official release of the DMControl Generalization Benchmark 2 (DMC-GB2)

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning