StarCraft II Learning Environment

JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"

Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab

OpenAI Gym wrapper for the DeepMind Control Suite

Jax implementation of "Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models"

📖 Paper: Deep Reinforcement Learning with Double Q-learning 🕹️

📖 Paper: Human-level control through deep reinforcement learning 🕹️

Implementing DeepMind's Fast Reinforcement Learning paper, and adding additional features to generalize the algorithms

Gymnasium integration for the DeepMind Control (DMC) suite

Farama Gymnasium API Wrapper for the DeepMind Control Suite and DeepMind Robot Manipulation Tasks

Open source code for AlphaFold.

I’ll be testing different Gemma models and sharing the results here and on my Hugging Face space. Stay tuned for updates!

NFNets and Adaptive Gradient Clipping for SGD implemented in PyTorch. Find explanation at tourdeml.github.io/blog/

MLP-Mixer: An all-MLP Architecture for Vision

This project implements an AI that learns the Snake game through Deep Q-Learning. It uses Fast Forward and CNN-based training to learn the optimal game strategy and visualises the learning process.

Construction of controllers for Shadow-Hand in Mujoco environment, using Deep Learning. 2 Different methods were used to create the controllers: a) Behavioral Cloning b) Deep Reinforcement Learning

Scalable distributed reinforcement learning agents on kubernetes

The code for the famous DQN paper applied on Atari's Breakout.

Applying DeepMind's MuZero algorithm to the cart pole environment in gym

Lernd is ∂ILP (dILP) framework implementation based on Deepmind's paper Learning Explanatory Rules from Noisy Data.