Deepfakes Software For All

Grok open release

A toolkit for developing and comparing reinforcement learning algorithms.

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

Model parallel transformers in JAX and Haiku

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

Causal Effect Inference with Deep Latent-Variable Models

OpenAI's cartpole env solver.

Clean Python Implementation of the Deep Deterministic Policy Gradients Algorithm

CFRBM is a implementation of the RBM model to the collaborative filtering task

Using a quantum computer to cluster data points

University Project, Reinforcement Learning with DQN on a modified cartpole scenario.

Perform basic image segmentation using discrete quadratic models (DQM) and hybrid solvers.