borislavmavrin Goto Github PK

agent

bert

TensorFlow code and pre-trained models for BERT

borislavmavrin.github.io

cs224n-a5

cs231n

deeprl

Code for my research papers: DQN, Quantile Regression DQN, Distributional Reinforcement Learning for Efficient Exploration, Deep RL with decorrelation

dnc

A TensorFlow implementation of the Differentiable Neural Computer.

dqn.replay_buffer

dune-legacy

Fork of Dune Legacy (an open source remake of Dune II: The Building of a Dynasty)

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

flask-circleci-heroku

A simple flask app with docker

homework

Assignments for CS294-112.

house-price-model

Hierarchical Spatial Regression Model for Edmonton, Canada

lab

A customisable 3D platform for agent-based AI research

opendune

DUNE, REINVENTED

original-dqn-docker

Original DeepMind's implementation of DQN to be run on nvidia-docker with modern gpu support (cuda 8)

pytorch-i-revnet

i-RevNet Pytorch Code

reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

retro-pytorch

Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch

reuters-full-data-set

Full dataset of Reuters composed of 8,551,441 news titles, links and timestamps (Jan 2007 - Aug 2016). Generate your own up to today!

rl.cs234.stanford.s2018

Complete written and coding solutions to CS234: Reinforcement Learning

rl.cs294.berkeley.f2017

Complete solutions to Berkley CS294: Deep Reinforcement Learning

stance-detection

LSTM, biconditional, soft attention LSTM/GRU encoders for SemEval 2016 stance detection task

text-classifier

general purpose text classification

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

ubuntu-server-autoinstall

Instructions and helper script to build ubuntu server auto installation iso

unreal

Reinforcement learning with unsupervised auxiliary tasks

vizdoom

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode:

wavernn

Pytorch implementation of Deepmind's WaveRNN model

word2vec

word2vec implementation with analystical gradients using NumPy.