A playbook for systematically maximizing the performance of deep learning models.

Libraries, tools and tasks created and used at DeepMind Robotics.

Tool kit for the Mujoco user

Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"

Simulating Kinect Noise: adding noise to clean depth-maps rendered with a graphics engine.

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

A Julia package for Spider Monkey Optimization.

A standalone library to randomize various OpenAI Gym Environments

Convert DeepMind Control Suite to OpenAI gym environments.

The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.

Mujoco model of the Kinova Gen3 robot

A platform for Reasoning systems (Reinforcement Learning, Contextual Bandits, etc.)

A Python Soft Robot Simulator Using Voxelyze

A large-scale benchmark and learning environment.

Python implementation of CMA-ES

Accelerated deep learning R&D

List of articles related to deep learning applied to music

Code for CoRL 2019 paper "TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer"

🤖 Poppy Ergo Jr is an open-source robotic arm based on modular 3D printed conception and low-cost XL-320 motors.

Readable implementation of a Capsule Network as described in "Dynamic Routing Between Capsules" [Hinton et. al.]

Dockerizing Multiple Services inside a Container

Using RGB Image as Visual Input for Mapless Robot Navigation

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

A Compositional Object-Based Approach to Learning Physical Dynamics

DHER: Hindsight Experience Replay for Dynamic Goals (ICLR-2019)

2D Gridworld navigation using RL with Hindsight Experience Replay

Author's PyTorch implementation of TD3 for OpenAI gym tasks