Mathieu-Seurin

baxter_representation_learning_1D

follow_me_safely

impact-driven-exploration

impact-driven-exploration

neural_toolbox

Using Deep Model in multiple projects : Need same base code

baxter_representation_learning_3D

image_maze

Simple maze with augmented state to try RL agent

lets_doom_this

modulation_adaptation

Reproducing "FiLM: Visual Reasoning with a General Conditioning Layer" and testing other stuff

as-td

Baxter-School

cocoapi

COCO API - Dataset @ http://cocodataset.org/

codinterview

configPortable

Zsh, Emacs etc ...

dat-eeg

DeepRL-Grounding

Train an RL agent to execute natural language instructions in a 3D Environment (PyTorch)

FDMS-part2

few_words

gym-minigrid

Minimalistic gridworld environment for OpenAI Gym

gym-vizdoom

Gym wrapper for Vizdoom environments

project_base

random-network-distillation-pytorch

Random Network Distillation pytorch

safe_frozen_lake

Seamless_PV_power_forecasting

Seamless prediction of GHI using machine learning

sisyphe

Memorize poetry by hiding words progressively

tensorboard-aggregator

Aggregate multiple tensorboard runs to new summary or csv files

TextWorld

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

tf_rl_testing

Just wandering with tensorflow and some deep reinforcement learning

Timer

Personnal timer, stop watch, python 2

torch-ac

Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms: A2C and PPO

ZoeDepth

Metric depth estimation from a single image