Universal game AI system for game developer
Project description
System Overview
Universal game AI system. Game developers need to provide functions like those provided by Open-AI game, so they can train their game AI.
- Use Instructions
- 1.For games that use images as state
use “ init_UDQN(game, inputImageSize, choose_optimizers, learning_rate) “ to create your network object.
the object has the function “run(game, inputImageSize, total_steps, total_reward_list, num, step_num)” to train.
“ plot_cost() “ shows the gradient change graph
- 2.For games that take parameters as state
use “ Population(population_num) “ to create your Population object.
the object has the function “ initPopulation(self, net_in, net_h1, net_h2, net_out)” to create your network.
the object has the function “ runGame(game)” to train.
Environment Instructions
Python3.7+Graphaiz2.38
Directory Structure Instructions
HanhanAI
__init__.py
ga_brain.py
population
universal_dqn.py
LICENSE
README.rsd
setup.py
V2.0.2 version
Can save network
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for HanhanAI-2.0.2-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ca3277ef35cff88b990631bbad0686565e5f32d8a593fb68530e65229a0c684f |
|
MD5 | a5bd2c2b7b2610871bfc7564cbfb6e2b |
|
BLAKE2b-256 | f4a2947e503eebf8605f0688b3bd33fb85a2862b1537f5408352017e8877cc7a |