# mini-AlphaStar
## Update
This is the "v_0.8" version, and the updates are as follows:
* Add code for Levenshtein and Hamming distance;
* Add the function for fighting against built-in AI computer;
* Fix the SL training loss problem for select units;
## Introduction
We release the mini-AlphaStar project, which is a mini source version of the original AlphaStar program by DeepMind.
"v_0.X" means we think we have implemented above X * 10 percent code of it.
"mini" means that we make the original AlphaStar hyperparameter adjustable so that it can run on a small scale.
The readme for the Chinese version is at [here](README_CHS.MD).
## Contents
The below table shows the corresponding packages in the project.
Packages | Content
------------ | -------------
alphastarmini.core.arch | the alphaStar architecture
alphastarmini.core.sl | surpervised learning
alphastarmini.core.rl | reinforcement learning
alphastarmini.core.ma | multi-agent league traning
alphastarmini.lib | lib functions
alphastarmini.third | third party functions
res | other useful resources
## Requirements
Pytorch >= 1.5, others please see requirements.txt.
## Location
The codes are in these places:
Location | URL
------------ | -------------
Github | [https://github.com/liuruoze/mini-AlphaStar](https://github.com/liuruoze/mini-AlphaStar)
Gitee | [https://gitee.com/liuruoze/mini-AlphaStar](https://gitee.com/liuruoze/mini-AlphaStar)
## Furture
There are some parts that still need to be fulfilled, e.g., the calculation of z, the loss part of the vtrace, and some missing information of the env to be filled up.
## Citing
If you find this repository useful, please cite our project:
```
@misc{mini-AlphaStar,
author = {Ruo{-}Ze Liu and Wenhai Wang and Yang Yu and Tong Lu},
title = {mini-AlphaStar},
year = {2021},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/liuruoze/mini-AlphaStar}},
}
```
## Report
We will present a technical report to introduce the design and usage details of it in about one month.
## Paper
We will give a paper which may be available in the future presenting the experiments and evaluations on using it.
没有合适的资源?快使用搜索试试~ 我知道了~
mini-AlphaStar:这是DeepMind原始AlphaStar程序的迷你源代码版本
共84个文件
py:70个
md:6个
txt:4个
需积分: 13 6 下载量 166 浏览量
2021-03-30
20:33:58
上传
评论 1
收藏 158KB ZIP 举报
温馨提示
迷你AlphaStar 更新 这是“ v_0.8”版本,更新如下: 添加Levenshtein和汉明距离的代码; 增加了对抗内置AI计算机的功能; 解决了某些单位的SL训练损失问题; 介绍 我们发布了mini-AlphaStar项目,它是DeepMind原始AlphaStar程序的微型源版本。 “ v_0.X”表示我们认为我们已经在X * 10%以上的代码上实现了。 “ mini”意味着我们使原始的AlphaStar超参数可调,以便可以小规模运行。 中文版的自述文件在。 内容 下表显示了项目中的相应软件包。 配套 内容 alphastarmini.core.arch alphaStar体系结构 alphastarmini.core.sl 监督学习 alphastarmini.core.rl 强化学习 alphastarmini.core.ma 多代理联赛转换 alph
资源详情
资源评论
资源推荐
收起资源包目录
mini-AlphaStar-main.zip (84个子文件)
mini-AlphaStar-main
model
readme.md 43B
run.py 2KB
requirements.txt 151B
README.MD 2KB
res
sc2_typeenums.h 53KB
pseudcode
pseudocode
supervised.py 3KB
rl.py 21KB
alphastar.py 4KB
README.md 222B
multiagent.py 10KB
detailed-architecture.txt 26KB
LICENSE 11KB
README_ENG.MD 2KB
setup_cmd.txt 309B
data
readme.md 40B
.gitignore 407B
README_CHS.MD 2KB
alphastarmini
lib
config.py 433B
hyper_parameters.py 21KB
multinomial.py 1KB
edit_distance.py 3KB
alphastar_transformer.py 3KB
utils.py 9KB
__init__.py 19B
glu.py 2KB
core
ma
player.py 9KB
pfsp.py 647B
coordinator.py 705B
__init__.py 17B
ma_train.py 2KB
league.py 2KB
payoff.py 2KB
__init__.py 144B
sl
multi_node_training.py 1000B
load_pickle.py 2KB
load_feature_label.py 3KB
label.py 5KB
dataset.py 6KB
__init__.py 18B
load_replay_info.py 7KB
transform_replay_data.py 14KB
sl_train_by_tensor.py 5KB
feature.py 5KB
sl_train_by_pickle.py 5KB
dataset_pickle.py 6KB
balanced_data_parallel.py 4KB
arch
scalar_encoder.py 14KB
agent.py 29KB
location_head.py 13KB
target_unit_head.py 10KB
action_type_head.py 9KB
__init__.py 20B
delay_head.py 5KB
spatial_encoder.py 11KB
arch_model.py 13KB
core.py 5KB
entity_encoder.py 37KB
queue_head.py 5KB
selected_units_head.py 14KB
readme.txt 104B
rl
alphastar_agent.py 9KB
baseline.py 10KB
utils.py 3KB
state.py 2KB
against_computer.py 11KB
__init__.py 18B
env_run_loop.py 3KB
env_utils.py 3KB
learner.py 4KB
action.py 9KB
rl_train.py 2KB
compute_loss.py 42KB
actor.py 11KB
__init__.py 112B
third
__init__.py 63B
transformer
Layers.py 2KB
__init__.py 27B
Modules.py 674B
LICENSE 1KB
Optim.py 1KB
Translator.py 4KB
Constants.py 75B
Models.py 6KB
SubLayers.py 3KB
共 84 条
- 1
侯戈
- 粉丝: 19
- 资源: 4630
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0