/A3CSuperMario_Windows

SuperMario A3C Trainer for windows

Primary LanguagePythonApache License 2.0Apache-2.0

A3CSuperMario_Windows

result

alt text

3 threads

after 4000 episodes, about 30% chance of Clearance

after 8000 episodes, about 70% chance of Clearance

Enviroment

Install NES emulator FCEUX

lua scripts and nes files in 'SuperMarioBros' Folder are modified from gym-super-mario

Install pywin32

using win32 named pipe to comunicate with FCEUX, so support winodws only

Config

config.py

FCEUX_PATH = 'D:\\fceux-2.2.3-win32\\fceux.exe'

change to your install path

A3CTrainer.py

load_model = False

change to True if you need to continue training

Run

Train

python A3CTrainer.py

Test

python A3CTester.py

A3C model

introduction article to this impelement

A3C model implements is from this article 《simple-reinforcement-learning-with-tensorflow-part-8-asynchronous-actor-critic-agents-a3c》.

I have tried a lot of A3C implements and this one is most efficient.