watchernyu Goto Github PK

action-gradient-descent

Work in progress

adversarial-squad

Code from Jia and Liang, "Adversarial Examples for Evaluating Reading Comprehension Systems" (EMNLP 2017)

ai-fun-stuff

A list of references to fun stuff to read or watch or interact with

airbnb-visualization-nyc

anonymized_test

test only

auto_ml_trainer

bail

cisco-anyconnect-ubuntu

This is a short guide on using cisco anyconnect vpn on ubuntu

coding

combination

d4rl

A collection of reference environments for offline reinforcement learning

deep_rl

deeplearning.ai-pytorch

PyTorch Implementations of Coursera's Deep Learning(deeplearning.ai) Specialization

general-dl-resources

github-practice

gitignore

A collection of useful .gitignore templates

hindsight-experience-replay

This is the pytorch implementation of Hindsight Experience Replay (HER) - Experiment on all fetch robotic environments.

jarcraft-poe

Portfolio Online Evolution implemented in JarCraft combat simulator

jarcraft-poe-old

judge_embedding

latex-table-plotter-python

This repo is a very very simple program that convert 2-D python array into latex table code, then you can just copy paste the output to your Latex file.

mageacademy

matchlstm-analyze-adversarial-training

Using match-lstm and SQuAD dataset to test how different settings of adversarial training affect model robustness

math-of-stats-datascience

A repo hosting code for some math tools learned in math of stats and datascience class

mcts

Minimal implementation of MCTS for my own reference

me

https://watchernyu.github.io/me/

metaworld

An open source robotics benchmark for meta- and multi-task reinforcement learning

minimal

Minimal is a Jekyll theme for GitHub Pages

mj_envs

A collection of MuJoCo based environments.

mjrl

Reinforcement learning algorithms for MuJoCo tasks