Marco Birck's Projects
Pytorch implementation of Adaptative Dropout a.ka Standout.
Course code repository for Firebase in a Weekend by Google: Android
Udacity course, implementations and code.
Implementation of WGAN to generation of Atari Games Images. (GAN, WGAN, ATARI, Generative)
Attentional Mechanism incorporated in Asynchronous Advantage Actor Critic a3c/a2c deep mind
Repositorie containing solutions for the Berkeley CS188 class.
D'ont need one
#WORK IN PROGRESS PyTorch Implementation of Supervised and Deep Q-Learning EWC(Elastic Weight Consolidation), introduced in "Overcoming Catastrophic Forgetting in Neural Networks"
Code and stuff from Stanford course on Tensorflow
My content of CS294 Deep Reinforcement Learning course, conduced by Sergey Levine from UC Berkeley.
Using Keras and Deep Deterministic Policy Gradient to play TORCS
Solutions for the labs in Deep RL Bootcamp.
Plenty of Deep Learning resources in companion with notebooks, for learning purposes.
DQN implementation in Keras + TensorFlow + OpenAI Gym
I replicate and make the original Seq2Seq from PyTorch tutorials to be easy to use and adapt.
Geolocation generic classifier using siamese neural networks using TensorFlow and Keras.
Let me try pimp a city with amazing graffitis
Repository with lots of useful ipython notebooks
Extension of https://github.com/ikostrikov/pytorch-a2c-ppo-acktr, making it feasible to run train on multiple games simultaneously.
Extension of https://github.com/openai/baselines, making it feasible to run train on multiple games simultaneously.
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks" in PyTorch
Attempt to implement A2C and PPO algorithm with modular properties of Maxout and LWTA. # UNFINISHED AND FAILED
Paper List I have read or will read, just to keep control. (I should have done this before!!!)
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
PyTorch implementation of DeepMind's PNAS 2017 paper "Overcoming Catastrophic Forgetting"
Bring some LR schedulers from Keras to PyTorch.