Panda Gym alternatives for AI agents.

Dream to Control: Learning Behaviors by Latent Imagination

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

A modular high-level library to train embodied AI agents across a variety of tasks and environments.

A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning

Guided Policy Search

OpenMMLab Foundational Library for Training Deep Learning Models

btx0424/OmniDrones is a high-star GitHub project relevant to AI agent workflows.

:earth_americas: Simple and ready-to-use tutorials for TensorFlow

🦀 Low-level 3D Computer Vision library in Rust

ICCV2019 - Learning to Paint With Model-based Deep Reinforcement Learning

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

A simple interface for editing natural photos with generative neural networks.

Superfast AI decision making and intelligent processing of multi-modal data.

Mosaico - The data platform for Physical AI

Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds