Alejandro Escontrela

AMP_for_hardware. Code for "Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions"

gauss_gym. Python

Numpy-CNN. A numpy-only implementation of a Convolutional Neural Network, from the ground up.

viper_rl. Using advances in generative modeling to learn reward functions from unlabeled videos.

score_matching_rl. Code for the paper "Learning a Diffusion Model Policy from Rewards via Q-Score Matching"

DDP_Examples. Using Differential Dynamic Programming (DDP) to control various dynamical systems.

BabyFace. Baby monitoring device that uses MIT's "Eulerian Video Magnification" to detect heart beat based on facial colour changes.

skip_rnn. A simple skip-rnn model created with NumPy.

MPO-JAX. Maximum A Posteriori Policy Optimization

Ale. repo for my github pages website

TradingGym. Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.

escontra.

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"