chrisguo

beijing_fushengji

北京浮生记PC版源代码

worktime

定位为项目管理，BUG管理。特点是容易安装，使用方便，界面简单友好。

DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

reinforcement-learning-an-introduction

Python code for Reinforcement Learning: An Introduction

Reinforcement_Learning_Blog

This code is written for the blogs

awesome-rl

Reinforcement learning resources curated

DeepLearningVideoGames

dot-emacs

dot emacs

Easy21

:rocket: Reinforcement Learning Assignment

Easy21-RL

solutions to David Silver's RL course project Easy21

game_design_art

notes on game design art

git-cheat

the easy way to use git

LatentDirichletAllocation

linux_commands

the most used commands of linux

michi

Minimalistic Go MCTS Engine

multi_armed_bandit

npc_marriage

the NPC's marriage simulation in RPG game

r-notes

some notes for R language

reinforcement-learning

Implementing exercises from Reinforcement Learning: An Introduction

RL_PolicyIteration

A solution in Python for Monte Carlo Control, Temporal difference (Sarsa) and Linear Approximation variants of policy iteration reinforcement learning algorithms, in context of learning the optimal policy for a variant of Blackjack toy problem, called Easy21.

Temporal-Difference-Learning

Temporal Difference Learning and Basic Reinforcement Learning Demos in Matlab