queenstina Goto Github PK

30min_guides

覃健祥的学习笔记，各种几十分钟入门的文档

aamas-2015-efficient

Information to reproduce the AAMAS 2015 "Efficient Inter-Team Task Allocation in RoboCup Rescue" paper experiments

activetransferlearning

Code for various active transfer learning projects.

auctions

Auction Theory Toolbox – Computer Verified Auctions

awesome-courses

:books: List of awesome university courses for learning Computer Science!

awesome-rl

Reinforcement learning resources curated

basic_reinforcement_learning

An introduction series to Reinforcement Learning (RL) with comprehensive step-by-step tutorials.

cartpole_ai

CartPole with DQN

deep-rl-mountain-car

DQN based RL agent for Mountain Car

deep_qlearning_cartpole

My Journey Into Deep Q-Learning with Keras and Gym

electronic-wechat

:speech_balloon: A better WeChat on macOS and Linux. Built with Electron by Zhongyi Tong.

examples-in-python

fann

Official github repository for Fast Artificial Neural Network Library (FANN)

flappybirdrl

Flappy Bird hack using Reinforcement Learning

hfo

Half Field Offense in Robocup 2D Soccer

keepaway

RoboCup Keepaway benchmark player framework.

keepaway-1

keepaway-2

keepawaysim

This simulator runs an experiment to test policy transfer with behavioral diversity for a multi-agent task using Keepaway Soccer task as a multi-agent benchmark task. This work is for a paper on "Policy transfer for multi-agent learning through neuro-evolution with behavioral diversity". This software is based on the RoboCupSharp benchmark task by Phillip Verbancsics.

lantern

:zap: Open Internet for everyone. Lantern is a free desktop application that delivers fast, reliable and secure access to the open Internet for users in censored regions. It uses a variety of techniques to stay unblocked, including P2P and domain fronting. Lantern relies on users in uncensored regions acting as access points to the open Internet.

latexdraw

A vector drawing editor for LaTeX.

lspi-cpp

A C++ implementation of the Least Squared Policy Iteration machine learning algorithm with the inverted pendulum problem.

machinelearning

Basic Machine Learning and Deep Learning

mastering-emacs-in-one-year-guide

Be great at emacs in one year

minirank

Ranking and ordinal regression algorithms in Python

mmdgm

Code for Max-margin Deep Generative Models (NIPS15)

mountaincar

Solving the mountain car problem with the use of tile coding and the reinforcement learning algorithm Expected SARSA

nn-from-scratch

Implementing a Neural Network from Scratch

nnc

Quadcopter stability using reinforcement learning

notepadqq

Notepad++-like editor for Linux