AI Agent Skills

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

google-deepmind/gemini-robotics-sdk is a high-star GitHub project relevant to AI agent workflows.

StarCraft II Learning Environment

TensorFlow-based neural network library

JAX-based neural network library

A customisable 3D platform for agent-based AI research

Optax is a gradient processing and optimization library for JAX.

A library for generative social simulation

Learning to Learn in TensorFlow

Tracking Any Point (TAP)

An interactive HTML pretty-printer for machine learning research in IPython notebooks.

PIX is an image processing library in JAX, for JAX.

Second Order Optimization and Curvature Estimation with K-FAC in JAX.

A collection of tabletop tasks in Mujoco

Tutorial on how to get started with MuJoCo Simulation Platform. MuJoCo stands for Multi-Joint dynamics with Contact. It was acquired and made freely available by DeepMin…

This's an implementation of deepmind Visual Interaction Networks paper using pytorch