معرفی شرکت ها

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

تبلیغات ما

مشتریان به طور فزاینده ای آنلاین هستند. تبلیغات می تواند به آنها کمک کند تا کسب و کار شما را پیدا کنند.

مشاهده بیشتر

توضیحات

DIAMBRA™ Arena. Built with OpenAI Gym Python interface, easy to use, transforms popular video games into Reinforcement Learning environments

ویژگی	مقدار
سیستم عامل	-
نام فایل	diambra-arena-2.1.0rc6
نام	diambra-arena
نسخه کتابخانه	2.1.0rc6
نگهدارنده	[]
ایمیل نگهدارنده	[]
نویسنده	DIAMBRA Team
ایمیل نویسنده	info@diambra.ai
آدرس صفحه اصلی	https://github.com/diambra/arena
آدرس اینترنتی	https://pypi.org/project/diambra-arena/
مجوز	Custom

<img src="https://raw.githubusercontent.com/diambra/arena/main/img/github.png" alt="diambra" width="100%"/> <a href="https://docs.diambra.ai">Documentation</a> • <a href="https://diambra.ai/">Website</a> <a href="https://www.linkedin.com/company/diambra">Linkedin</a> • <a href="https://diambra.ai/discord">Discord</a> • <a href="https://www.twitch.tv/diambra_ai">Twitch</a> • <a href="https://www.youtube.com/c/diambra_ai">YouTube</a> • <a href="https://twitter.com/diambra_ai">Twitter</a> <a href="https://arxiv.org/abs/2210.10595"><img src="http://img.shields.io/badge/paper-arxiv.2210.10595-B31B1B.svg" alt="Paper"/></a> # DIAMBRA Arena ## Index - **[Overview](#overview)** - **[Competition Platform](#competition-platform)** - **[Installation](#installation)** - **[Quickstart & Examples](#quickstart--examples)** - **[Reinforcement Learning Libs Compatibility](#reinforcement-learning-libs-compatibility)** - **[References](#references)** - **[Support, Feature Requests & Bugs Reports](#support-feature-requests--bugs-reports)** - **[Citation](#citation)** - **[Terms of Use](#terms-of-use)** ## Overview DIAMBRA Arena is a software package featuring a collection of **high-quality environments for Reinforcement Learning research and experimentation**. It provides a standard interface to popular arcade emulated video games, offering a **Python API fully compliant with OpenAI Gym format**, that makes its adoption smooth and straightforward. It **supports all major Operating Systems** (Linux, Windows and MacOS) and **can be easily installed via Python PIP**, as described in the **[installation section](#installation)** below. It is **completely free to use**, the user only needs to <a href="https://diambra.ai/register/" target="_blank">register on the official website</a>. In addition, it comes with a <a href="https://docs.diambra.ai" target="_blank">comprehensive documentation</a>, and this repository provides a **collection of examples** covering main use cases of interest **that can be run in just a few steps**. #### Main Features All environments are episodic Reinforcement Learning tasks, with discrete actions (gamepad buttons) and observations composed by screen pixels plus additional numerical data (RAM values like characters health bars or characters stage side). They all **support both single player (1P) as well as two players (2P) mode**, making them the perfect resource to explore all the following Reinforcement Learning subfields: | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/AIvsCOM.png" alt="standardRl" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/AIvsAI.png" alt="competitiveMa" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/AIvsHUM.png" alt="competitiveHa" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/SP.png" alt="selfPlay" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/IL.png" alt="imitationLearning" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/HITL.png" alt="humanInTheLoop" width="125"/> | | :-------------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------: | :---------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------: | | Standard RL | Competitive Multi-Agent | Competitive Human-Agent | Self-Play | Imitation Learning | Human-in-the-Loop | #### Available Games Interfaced games have been selected among the most popular fighting retro-games. While sharing the same fundamental mechanics, they provide slightly different challenges, with specific features such as different type and number of characters, how to perform combos, health bars recharging, etc. Whenever possible, games are released with all hidden/bonus characters unlocked. Additional details can be found in the <a href="https://docs.diambra.ai/envs/games/" target="_blank">dedicated section</a> of our Documentation. | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/doapp.jpg" alt="doapp" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/sfiii3n.jpg" alt="sfiii3n" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/tektagt.jpg" alt="tektagt" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/umk3.jpg" alt="umk3" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/samsh5sp.jpg" alt="samsh6sp" width="125"/> | <img src="https://raw.githubusercontent.com/diambra/arena/main/img/kof98umh.jpg" alt="kof98umh" width="125"/> | | :------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------: | :------------------------------------------------------------------------------------------------------------------: | | Dead Or Alive ++ | Street Fighter III 3rd Strike | Tekken Tag Tournament | Ultimate Mortal Kombat 3 | Samurai Showdown 5 Special | The King of Fighers '98 Ultimate Match Hero | **Many more are coming soon...** ## Competition Platform <img src="https://raw.githubusercontent.com/diambra/arena/main/img/leaderboard.jpg" alt="DIAMBRA Leaderboard" width="100%"/> Our competition platform allows you to submit your agents and compete with other coders around the globe in epic video games tournaments! It features a public global leaderboard where users are ranked by the best score achieved by their agents in our different environments. It also offers you the possibility to unlock cool achievements depending on the performances of your agent. <img src="https://raw.githubusercontent.com/diambra/arena/main/img/achievements.jpg" alt="DIAMBRA Achievements" width="100%"/> Submitted agents are evaluated and their episodes are streamed on our Twitch channel. We aimed at making the submission process as smooth as possible, **<a href="https://diambra.ai/register/" target="_blank">join us and try it now!</a>** ## Installation - <a href="https://diambra.ai/register/" target="_blank">Create an account on our website</a>, it requires just a few clicks and is 100% free - Install Docker Desktop: <a href="https://docs.docker.com/desktop/install/linux-install/" target="_blank">Linux</a> | <a href="https://docs.docker.com/desktop/windows/install/" target="_blank">Windows</a> | <a href="https://docs.docker.com/desktop/mac/install/" target="_blank">MacOS</a> - Install DIAMBRA Command Line Interface: `python3 -m pip install diambra` - Install DIAMBRA Arena: `python3 -m pip install diambra-arena` **Using a virtual environment to isolate your python packages installation is strongly suggested** ## Quickstart & Examples DIAMBRA Arena usage follows the standard RL interaction framework: the agent sends an action to the environment, which process it and performs a transition accordingly, from the starting state to the new state, returning the observation and the reward to the agent to close the interaction loop. The figure below shows this typical interaction scheme and data flow. <img src="https://raw.githubusercontent.com/diambra/arena/main/img/basicUsage.png" alt="rlScheme" width="75%"/> #### Download Game ROM(s) and Check Validity Check available games with the following command: ``` diambra arena list-roms ``` Output example: ```shell [...] Title: Dead Or Alive ++ - GameId: doapp Difficulty levels: Min 1 - Max 4 SHA256 sum: d95855c7d8596a90f0b8ca15725686567d767a9a3f93a8896b489a160e705c4e Original ROM name: doapp.zip Search keywords: ['DEAD OR ALIVE ++ [JAPAN]', 'dead-or-alive-japan', '80781', 'wowroms'] Characters list: ['Kasumi', 'Zack', 'Hayabusa', 'Bayman', 'Lei-Fang', 'Raidou', 'Gen-Fu', 'Tina', 'Bass', 'Jann-Lee', 'Ayane'] [...] ``` Search ROMs on the web using **Search Keywords** provided by the game list command reported above. **Pay attention, follow game-specific notes reported there, and store all ROMs in the same folder, whose absolute path will be referred in the following as** `your/roms/local/path`. **Specific game ROM files are required, check validity of the downloaded ROMs as follows.** Check ROM(s) validity running: ``` diambra arena check-roms your/roms/local/path/romFileName.zip ``` The output for a valid ROM file would look like the following: ``` Correct ROM file for Dead Or Alive ++, sha256 = d95855c7d8596a90f0b8ca15725686567d767a9a3f93a8896b489a160e705c4e ``` **Make sure to check out our <a href="https://diambra.ai/terms" target="_blank">Terms of Use</a>, and in particular Section 7. By using the software, you accept the in full.** #### Base script Running a complete episode with a random agent requires less than 20 python lines: ```python {linenos=inline} import diambra.arena env = diambra.arena.make("doapp") observation = env.reset() while True: env.render() actions = env.action_space.sample() observation, reward, done, info = env.step(actions) if done: observation = env.reset() break env.close() ``` To execute the script run: ``` diambra run -r your/roms/local/path python script.py ``` Additional details and use cases are provided in the <a href="https://docs.diambra.ai/gettingstarted/" target="_blank">Getting Started</a> section of the documentation. ### Examples The `examples/` folder contains ready to use scripts representing the most important use-cases, in particular: - Single Player Environment - Multi Player Environment - Wrappers Options - Human Experience Recorder - Imitation Learning These examples show how to leverage both single and two players modes, how to set up environment wrappers specifying all their options, how to record human expert demonstrations and how to load them to apply imitation learning. They can be used as templates and starting points to explore all the features of the software package. <img src="https://raw.githubusercontent.com/diambra/arena/main/img/github.gif" alt="diambraGif" width="100%"/> ## Reinforcement Learning Libs Compatibility DIAMBRA Arena is built to maximize compatibility will all major Reinforcement Learning libraries. It natively provides interfaces with the two most import packages: Stable Baselines (both version 2 and 3) and Ray RLlib. Their usage is illustrated in detail in the <a href="https://docs.diambra.ai/handsonreinforcementlearning/" target="_blank">documentation</a> and in the <a href="https://github.com/diambra/agents" target="_blank">DIAMBRA Agents repository</a>. It can easily be interfaced with any other package in a similar way. Native interfaces, that can be installed with the dedicated options listed below, have been tested with the following versions: - Stable Baselines 3 | `pip install diambra-arena[stable-baselines3]` (<a href="https://stable-baselines3.readthedocs.io/en/master/index.html" target="_blank">Docs</a> - <a href="https://github.com/DLR-RM/stable-baselines3" target="_blank">GitHub</a> - <a href="https://pypi.org/project/stable-baselines3/" target="_blank">Pypi</a>): 1.6.1 - Ray RLlib | `pip install diambra-arena[ray-rllib]` (<a href="https://docs.ray.io/en/latest/index.html" target="_blank">Docs</a> - <a href="https://github.com/ray-project/ray" target="_blank">GitHub</a> - <a href="https://pypi.org/project/ray/" target="_blank">Pypi</a>): 2.0.0 - Stable Baselines | `pip install diambra-arena[stable-baselines]` (<a href="https://stable-baselines.readthedocs.io/en/master/index.html" target="_blank">Docs</a> - <a href="https://github.com/hill-a/stable-baselines" target="_blank">GitHub</a> - <a href="https://pypi.org/project/stable-baselines/" target="_blank">Pypi</a>): 2.10.2 ## References - Documentation: <a href="https://docs.diambra.ai" target="_blank">https://docs.diambra.ai</a> - Paper: <a href="https://arxiv.org/abs/2210.10595" target="_blank">https://arxiv.org/abs/2210.10595</a> - Website: <a href="https://diambra.ai" target="_blank">https://diambra.ai</a> - Discord: <a href="https://diambra.ai/discord" target="_blank">https://diambra.ai/discord</a> - Linkedin: <a href="https://www.linkedin.com/company/diambra" target="_blank">https://www.linkedin.com/company/diambra</a> - Twitch: <a href="https://www.twitch.tv/diambra_ai" target="_blank">https://www.twitch.tv/diambra_ai</a> - YouTube: <a href="https://www.youtube.com/c/diambra_ai" target="_blank">https://www.youtube.com/c/diambra_ai</a> - Twitter: <a href="https://twitter.com/diambra_ai" target="_blank">https://twitter.com/diambra_ai</a> ## Support, Feature Requests & Bugs Reports To receive support, use the dedicated channel in our <a href="https://diambra.ai/discord" target="_blank">Discord Server</a>. To request features or report bugs, use the <a href="https://github.com/diambra/arena/issues" target="_blank">GitHub Issue Tracker</a>. ## Citation Paper: <a href="https://arxiv.org/abs/2210.10595" target="_blank">https://arxiv.org/abs/2210.10595</a> ```LaTex @article{Palmas22, author = {{Palmas}, Alessandro}, title = "{DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation}", journal = {arXiv e-prints}, keywords = {reinforcement learning, transfer learning, multi-agent, games}, year = 2022, month = oct, eid = {arXiv:2210.10595}, pages = {arXiv:2210.10595}, archivePrefix = {arXiv}, eprint = {2210.10595}, primaryClass = {cs.AI} } ``` ## Terms of Use DIAMBRA Arena software package is subject to our <a href="https://diambra.ai/terms" target="_blank">Terms of Use</a>. By using it, you accept them in full. ###### DIAMBRA™ is a Trade Mark, © Copyright 2018-2023. All Rights Reserved.

نیازمندی

مقدار	نام
>=21	pip
-	setuptools
>=1	distro
<=0.21.0	gym
-	inputs
-	screeninfo
-	tk
>=4.4.0.42	opencv-python
-	grpcio
>=2.1.0rc7	diambra-engine
-	dacite
<=4.12.0	importlib-metadata
==2.0.0	ray[rllib]
<=2.10.0	tensorflow
<=1.12.1	torch
-	pyyaml
==2.10.2	stable-baselines
==3.20.1	protobuf
-	pyyaml
==1.6.1	stable-baselines3[extra]
-	pyyaml
-	pytest
-	pytest-mock
-	testresources

نحوه نصب

نصب پکیج whl diambra-arena-2.1.0rc6:

pip install diambra-arena-2.1.0rc6.whl

نصب پکیج tar.gz diambra-arena-2.1.0rc6:

pip install diambra-arena-2.1.0rc6.tar.gz