• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

deepmind/pycolab: A highly-customisable gridworld game engine with some batterie ...

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

deepmind/pycolab

开源软件地址(OpenSource Url):

https://github.com/deepmind/pycolab

开源编程语言(OpenSource Language):

Python 100.0%

开源软件介绍(OpenSource Introduction):

The pycolab game engine.

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

Play some games!

If you're new, why not try playing some games first? For the full colour experience on most UNIX-compatible systems:

  1. crack open a nice, new, modern terminal (iterm2 on Mac, gnome-terminal or xterm on linux). (Avoid screen/tmux for now---just the terminal, please.)
  2. set the terminal type to xterm-256color (usually, you do this by typing export TERM=xterm-256color at the command prompt).
  3. run the example games! One easy way is to cd to just above the pycolab/ library directory (that is, cd to the root directory of the git repository or the distribution tarball, if you're using either of those) and run python with the appropriate PYTHONPATH environment variable. Example command line for bash-like shells: PYTHONPATH=. python -B pycolab/examples/scrolly_maze.py.

Okay, install some dependencies first.

If that didn't work, you may need to obtain the following software packages that pycolab depends on:

  1. Python 2.7, or Python 3.4 and up. We've had success with 2.7.6, 3.4.3, and 3.6.3; other versions may work.
  2. Numpy. Our version is 1.13.3, but 1.9 seems to have the necessary features.
  3. Scipy, but only for running one of the examples. We have 0.13.3.

Overview

pycolab is extensively documented and commented, so the best ways to understand how to use it are:

  • check out examples in the examples/ subdirectory,
  • read docstrings in the .py files.

For docstring reading, the best order is probably this one---stopping whenever you like (the docs aren't going anywhere...):

  1. the docstring for the Engine class in engine.py
  2. the docstrings for the classes in things.py

Those two are probably the only bits of "required" reading in order to get an idea of what's going on in examples/. From there, the following reading may be of interest:

  1. plot.py: how do game components talk to one another---and how do I give the agent rewards and terminate episodes?
  2. human_ui.py: how can I try my game out myself?
  3. prefab_parts/sprites.py: useful Sprite subclasses, including MazeWalker, a pixel that can walk around but not through walls and obstacles.
  4. cropping.py: how can I generate the illusion of top-down scrolling by cleverly cropping an observation around a particular moving game element? (This is a common way to build partial observability into a game.)

Don't forget that you can always read the tests, too. These can help demonstrate by example what all the various components do.

Disclaimer

This is not an official Google product.

We just thought you should know that.




鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap