eyounx

VirtualTaobao

Virtual-Taobao simulators with OpenAI Gym interface

ZOOpt

A python package of Zeroth-Order Optimization (ZOOpt)

RetroCodes

Codes of our team for the OpenAI Retro Contest of reinforcement learning

RACOS

A theoretically-grounded derivative-free optimization method, born from a statistical view of evolutionary algorithms

ASG

Open category classification by adversarial sample generation

GANMM

Mixture of Generative Adversarial Networks for Clustering

MLSim

A machine learning based fine-grained disease transmission simulator

PRR

Meta-Reinforcement Learning with Policy Residual Representation

BILC

Binary Linear Compression for Multi-label Classification

mind-SC2

Efficient Reinforcement Learning with a Mind-Game for Full-Length StarCraft II

SRE

Sequential Random Embedding for High-Dimensional Derivative-Free Optimization

ZOOclient.jl

Client of distributed ZOOpt in Julia

POSEC

Learning Environmental Calibration Actions for Policy Self-Evolution

Deep-Reasoning-Papers

Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, planning and any other topics connecting deep learning and reasoning

ZOOsrv

Servers of distributed ZOOpt in Python

ABL-HED

Handwritten Equations Decipherment with Abductive Learning

Data

ExpSRacos

eyounx.github.io

Used as the AWRL Website

gym

A toolkit for developing and comparing reinforcement learning algorithms.

TMP