2048-api
A 2048 game api for training supervised learning (imitation learning) or reinforcement learning agents
Code structure
game2048/
: the main package.game.py
: the core 2048Game
class.agents.py
: theAgent
class with instances.displays.py
: theDisplay
class with instances, to show theGame
state.expectimax/
: a powerful ExpectiMax agent by here.
data/
: the main package.data_eval.csv
: the evaset to evaluate model generalization ability.dataprocess.py
: theData
class, to generate training data. Other functions or classes relate to data procession is also included.dataprocess_old.py
: theData
class, discarded.test.py
: several instances of IO function.
model_related/
: the main package.eval.py
: theeval
function with instances.logger.py
: theLogger
class, to launch tensorboard.model.py
: theConvNet
class, the DNN used to complete the 2048 game.train.py
: the program used to train the model.train_test.py
: used to evaluate the ability of the initial model.
explore.ipynb
: introduce how to use theAgent
,Display
andGame
.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
from game2048.agents import Agent
class YourOwnAgent(Agent):
def step(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)
return direction
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 course project requirements and description.