My 2048

A 2048 game api for training supervised learning (imitation learning) or reinforcement learning agents

Code structure

• game2048/: the main package.
  • game.py: the core 2048 Game class.
  • agents.py: 定义了 MyAgent ，用到Net.py和model/里的model.pth.
  • displays.py: the Display class with instances, to show the Game state.
  • expectimax/: a powerful ExpectiMax agent by here.
• Net.py:定义了卷积神经网络。
• train.py:训练模型的函数，包括加载数据集，数据预处理，模型训练。运行此代码得到model.pth并保存在model文件夹里。
• model/:模型文件model.pth。
• DataSet/:运行training_data.py得到数据集。
• explore.ipynb: introduce how to use the Agent, Display and Game.
• static/: frontend assets (based on Vue.js) for web app.
• webapp.py: run the web app (backend) demo.
• evaluate.py: evaluate your self-defined agent.

Requirements

• code only tested on linux system (ubuntu 16.04)
• Python 3 (Anaconda 3.6.3 specifically) with numpy and flask

To define your own agents

fromgame2048.agentsimportAgentclassYourOwnAgent(Agent):
defstep(self):
'''To define the agent's 1-step behavior given the `game`. You can find more instance in [`agents.py`](game2048/agents.py). :return direction: 0: left, 1: down, 2: right, 3: up '''direction=some_function(self.game)
returndirection

To compile the pre-defined ExpectiMax agent

cd game2048/expectimax
bash configure
make

To run the web app

python webapp.py

LICENSE

The code is under Apache-2.0 License.

For EE369 students from SJTU only

Please read here.