hiwonjoon Goto Github PK

atari-irl

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

caffe

Caffe: a fast open framework for deep learning.

char-rnn

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

cityscapesscripts

README and scripts for the Cityscapes Dataset

coinrun

Code for the paper "Quantifying Transfer in Reinforcement Learning"

convlstm

Spatio-temporal video autoencoder with convolutional LSTMs

convnetjs

Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

corl2019-drex

Code and project page for D-REX algorithm from the paper "Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations" presented at CoRL 2019.

cs294-deep-rl-hw

Berkeley DeepRL Homework

cs391-reinforce

HW4 - Car Envrionment

cycle-gan-tf

Reimplementation of cycle-gan(https://arxiv.org/pdf/1703.10593.pdf) with improved w-gan(https://arxiv.org/abs/1704.00028) loss in tensorflow.

dm_control

The DeepMind Control Suite and Package

dotfiles

:house: Personal dotfiles for *NIX systems

dotfiles_depreciated

dqn-tensorflow

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

eccv16-taxonomy

Code for ECCV 2016 paper, Taxonomy-Regularized Semantic Deep Convolutional Neural Networks

eccv2016-attr-old

estool

Evolution Strategies Tool

faster-rcnn_tf

Faster-RCNN in Tensorflow

fb.resnet.torch

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

flann

Fast Library for Approximate Nearest Neighbors

gcm

http://meslab.snu.ac.kr/courses/2014s/project/

gslicr

gSLICr: Real-time super-pixel segmentation

gym-miniworld

Simple 3D interior simulator for RL & robotics research

hiwonjoon.github.io

My personal blog

icml2019-trex

icra2019-activity-localize

Code for One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video, ICRA 2019

imagenet_regression

implicit_q_learning