mmcenta

berkeley-deeprlcourse

Solutions to homework assignments for Berkeley's Deep RL Course for Fall 2019.

deep-pool

Simple pool detector for satellite images.

discrete-embeddings

Diverse VAE experiments and implementations in TensorFlow.

dSLC

Distributed SIngle-Linkage Clustering in C++ with MPI.

gym-text2048

2048 as an OpenAI Gym environment with a simple text display.

jax-baselines

Implementation of core Deep Reinforcement Learning Algorithms with JAX.

left-shift

Using deep reinforcement learning to tackle the game 2048.

missing-link

Link prediction on the french web.

stanford-cs330

Solutions to homework assignments for Stanford's CS 330 Deep Multi-Task and Meta Learning Course for Fall 2019.

rlberry

An easy-to-use reinforcement learning library for research and education.

mmcenta/left-shift

Using deep reinforcement learning to tackle the game 2048.

mmcenta/stanford-cs330

Solutions to homework assignments for Stanford's CS 330 Deep Multi-Task and Meta Learning Course for Fall 2019.

mmcenta/gym-text2048

2048 as an OpenAI Gym environment with a simple text display.

mmcenta/berkeley-deeprlcourse

Solutions to homework assignments for Berkeley's Deep RL Course for Fall 2019.

mmcenta/eye-disease-recognition

Deep learning methods for recognizing eye disease in medical images.

mmcenta/jax-baselines

Implementation of core Deep Reinforcement Learning Algorithms with JAX.

mmcenta/discrete-embeddings

Diverse VAE experiments and implementations in TensorFlow.

mmcenta/first-order-methods

First order methods for regression models. Assignment for the MAP569 Machine Learning 2 course.

mmcenta/missing-link

Link prediction on the french web.

mmcenta/academic

mmcenta/Bayesian-RL

mmcenta/deepwalk

DeepWalk - Deep Learning for Graphs

mmcenta/default-prediction

Credit default prediction on a small dataset.

mmcenta/detr

End-to-End Object Detection with Transformers

mmcenta/helpful-bookworm

Tackling AutoNLP.

mmcenta/i-hate-sncf

Bot for monitoring TGVMax tickets because SNCF has no transparency.

mmcenta/mmcenta.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

mmcenta/muzero-general

MuZero

mmcenta/paper-notes

Notes on papers I've read.

mmcenta/rl-sutton-barto

Solutions to exercises proposed in the book Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto.

mmcenta/rlberry

An easy-to-use reinforcement learning library for research and education.

mmcenta/rld

mmcenta/simons-institute-workshops

Notes I've taken in Simons Institute workshops that I attended

mmcenta/sonnet

TensorFlow-based neural network library

mmcenta/spr

Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

mmcenta/starter-academic

mmcenta/TreeRNN

Integrating tree structures into recurrent neural networks for multi-label classification

mmcenta/vision

Datasets, Transforms and Models specific to Computer Vision

mmcenta/woptim

Using optimization to solve allocation problems.

mmcenta/youtube-flatland

Let's solve the flatland challenge!