Thomas Simonini

Deep_reinforcement_learning_Course. Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch

awesome-ai-tools-for-game-dev. A curated list of awesome AI tools for game developers

CatDCGAN. A DCGAN that generate Cat pictures 🐱‍💻

unity_ml_agents_course. Learn to create agents in Unity ML using Deep Reinforcement Learning with Tensorflow.

DNN-Speech-Recognizer. Built a deep neural network that functions as part of an end-to-end automatic speech recognition (ASR) pipeline.

the_mayan_adventure. The Mayan Adventure is an open-source reinforcement learning environment for Unity ML-Agents. In this environment, you train your agent (Indie) to find the golden statue in this dangerous environment full of traps.

jammo_the_robot.

ml-agents-snowball-fight. A multi-agent environment using Unity ML-Agents Toolkit

MLAgents-Tanks. A multi-agent environment using Unity ML-Agents Toolkit where two agents compete in a 1vs1 tank fight game

Time-series-prediction-and-text-generation. Built RNNs that can generate sequences based on input data - with a focus on two applications: used real market data in order to predict future Apple stock prices using an RNN model. The second one will be trained on Sir Arthur Conan Doyle's classic novel Sherlock Holmes and generates wacky sentences based on it that may - or may not - become the next great Sherlock Holmes novel.

AI_NANODEGREE-Computer-Vision-Capstone-Project-Facial-Keypoint-Detection-and-Real-time-Filtering. A CNN that make facial keypoint detection and real time filtering

Baselines_icm. [Work in Progress] ICM plugin for OpenAI Baselines

cifar-10-classifier-pytorch. A simple cifar-10 classifier with PyTorch

Dog-Breed-Classifier. Convolutional Neural Network that recognizes dog breeds

simple-A2C. A simple A2C made from scratch in PyTorch. Accompanying comic at https://hackernoon.com/intuitive-rl-intro-to-advantage-actor-critic-a2c-4ff545978752

Policy_gradients_CartPole. A Policy Gradient Learning with CartPole-v0 for Siraj Raval's challenge

ml-agents. Unity Machine Learning Agents Toolkit

News-Crawler-Parse-Backend. This is a crawler made with Scrapy.py to crawl french news articles and send them in your Parse.com backend

unity-api. C#

gym-games. A gym version of various games for reinforcenment learning.

squad_v1.1_for_question_generation. Python

huggingface_sb3. Additional code for Stable-baselines3 to load and upload models from the Hub.

GAN_implementations. Some GAN (Generative Adversarial Networks) implementations to generate MNIST images

random-network-distillation. Code for the paper "Exploration by Random Network Distillation"

baselines. OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

DLFN_Face_generator. A Generative Adversarial Network that generate human faces

style-transfer-pytorch. A Style Transfer agent that applies La Joconde's style to any picture [PROTOTYPE]

deep_q_learning. A DQL implementation with keras

Test_doom_dqn. Python

NewsSwipe. This version is for educational purposes only. The goal is to learn to create android applications with network. I create this app with the help of the excellent course : Udacity Android basics : networking

PlayBot_website. Website for a fake project : Playbot a bot that proposes games based on user tastes

StockHawk. An Android App that displays stock prices

reinforcement-learning. Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

Where_is_my_cat. A series of YOLO experimentations using DarkFlow

darknet. Convolutional Neural Networks

blog. Public repo for HF blog posts

DLFN_Image_classification. In this project, you'll classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. The dataset will need to be preprocessed, then train a convolutional neural network on all the samples. You'll normalize the images, one-hot encode the labels, build a convolutional layer, max pool layer, and fully connected layer. At then end, you'll see their predictions on the sample images.

simonini_thomas_website_new. My new personal website

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

DLFN_Language_Translation. A Seq-to-seq model that translates English to French

aind2-nlp-capstone. Recurrent Neural Network that translates English to French

deep-rl-course.

DeepRL-Agents. A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

AIND-VUI-Lab-Voice-Data. Python

Policy-Gradient-Doom--. Policy Gradient based agent that tries to survive in an hostile environement by collecting health.

dataiku-contrib. Public repository for DSS plugins

DGAN-Implementations. Some DGAN (Deep Generative Adversarial Networks) implementations to generate human faces

DLFN_Generate_The_Simpsons_Scripts. An RNN that generates new scripts for the Simpsons' tv show

better-unity-webgl-template. A better default template for Unity WebGL

sonictest.

SimpleLinearRegression_PhiladelphiaRateCrime_HousePricePrediction. This Machine Learning model helps us to predict of houses prices in Philadelphia region based on crime rate.

PlayBot. PlayBot is an AI that propose games based on user tastes

PlayBot_BackEnd. Playbot API in NodeJS