ml-agents0.7_宣布ML-Agents Unity软件包v1.0！

ml-agents0.7

On September 17, 2017, the first version of Unity Machine Learning Agents Toolkit (ML-Agents) was released. The mission was simple – allow game developers and AI researchers alike to use Unity as a platform to train and embed intelligent agents using the latest advancements in machine learning. Since our initial “Hello World” release, we’ve seen the community and development of the toolkit grow significantly, with the project amassing over 8400 GitHub stars. Today, after more than two and a half years of development and 15+ release updates, we are excited to announce that the ML-Agents Unity package has reached v1.0 and is available as a Preview package. We’re also launching a new product and resources page for ML-Agents.

2017年9月17日，发布了Unity Machine Learning Agents工具包(ML-Agents)的第一个版本。 任务很简单–让游戏开发人员和AI研究人员都可以使用Unity作为平台来利用最新的机器学习技术来训练和嵌入智能代理。 自从最初的“ Hello World”发行版以来，我们已经看到该工具包的社区和开发显着增长，该项目已累积了超过8400个GitHub明星。 今天，经过两年半的开发和15多个版本更新，我们很高兴地宣布ML-Agents Unity软件包已达到v1.0，并且可以作为预览软件包使用。 我们还将为ML-Agents启动一个新产品和资源页面 。

To give a bit of background – ML-Agents is an open-source project that enables games and simulations to serve as environments for training intelligent agents. It includes a C# SDK to set up a scene and define the agents within it, and a state-of-the-art machine learning library to train agents for 2D, 3D, and VR/AR environments.

给出一点背景知识– ML-Agents是一个开源项目，使游戏和模拟可以用作培训智能代理的环境。 它包括一个C＃SDK，用于设置场景并在其中定义代理，以及一个最新的机器学习库，用于训练2D，3D和VR / AR环境的代理。

Today, ML-Agents reached a significant milestone in becoming production-ready: the C# SDK has graduated to its first major version, v1.0, and is now available as a Preview package, com.unity.ml-agents, through the Unity Package Manager. This offers three key benefits to our users:

如今，ML-Agents已达到可投入生产的重要里程碑：C＃SDK已升级到其第一个主要版本v1.0，现在可通过Unity以Preview包com.unity.ml-agents的形式获得。包管理器。 这为我们的用户提供了三个主要好处：

• API stability. The ML-Agents C# SDK has evolved over more than two years of development and testing with our own demo Unity environments (ranging from locomotion tasks to multiplayer games and robotic arms) to real games made with Unity. The result is a flexible, feature-rich, and stable API that is easy to integrate into any game or Unity environment.

  API稳定性。 ML-Agents C＃SDK经过超过两年的开发和测试，已经通过我们自己的演示Unity环境(从运动任务到多人游戏和机械臂)到使用Unity制作的真实游戏进行了开发。 结果是灵活，功能丰富且稳定的API，可轻松集成到任何游戏或Unity环境中。

• Ease of installation. You can now get started with the ML-Agents Unity package directly from the Package Manager without the need to clone the GitHub project.

  易于安装。 现在，您可以直接从软件包管理器开始使用ML-Agents Unity软件包，而无需克隆GitHub项目。

• Verified Unity package (coming soon). The ML-Agents Unity package is now on track to become a Verified package for the 2020.2 version of the Unity Editor.

  经过验证的Unity软件包(即将推出)。 ML-Agents Unity软件包现在有望成为2020.2版Unity Editor的经过验证的软件包。

This blog post will walk you through a brief history of ML-Agents, overview our latest milestone release, ML-Agents Release 1, and offer a peek into upcoming ML-Agents improvements.

这篇博客文章将带您了解ML-Agent的简要历史，概述我们最新的里程碑发行版ML-Agents Release 1 ，并窥视即将到来的ML-Agent的改进。

ML-Agent的简要历史 (A brief history of ML-Agents)

In our inaugural blog post, we wrote:

在我们的第一篇博客文章中 ，我们写道：

As the world’s most popular creation engine, Unity is at the crossroads between machine learning and gaming. It is critical to our mission to enable machine learning researchers with the most powerful training scenarios, and for us to give back to the gaming community by enabling them to utilize the latest machine learning technologies.

作为世界上最受欢迎的创作引擎，Unity处于机器学习和游戏之间的十字路口。 对于我们的使命而言，至关重要的是使机器学习研究人员能够获得最强大的培训方案，并通过使他们能够利用最新的机器学习技术来回馈游戏界。

From simple to complex training environments in ML-Agents

ML-Agents中从简单到复杂的培训环境

Over the following two and half years, ML-Agents stayed true to its mission and evolved in the nexus of the Gaming and Machine Learning communities. We continuously improved the toolkit by adding new training options such as Curriculum Learning, enabling the Curiosity module for sparse-reward environments, improving the speed and efficiency of training, enabling Self-Play for multi-agent scenarios, and providing native, cross-platform inference support for all models trained with ML-Agents. (See our GitHub ML-Agents Overview page for a description of all the ML-Agents features.) We’ve seen firsthand how these improvements have enabled new demos and environments such as Puppo and integrations with real games such as Jam City’s Snoopy Pop and Carry Castle’s Source of Madness.

在接下来的两年半中，ML-Agent忠于其使命，并逐渐发展成为游戏和机器学习社区的纽带。 我们通过添加新的培训选项(例如课程学习) ，启用稀疏奖励环境的“ 好奇心”模块，提高培训的速度和效率，启用多代理场景的自玩功能以及提供本机跨平台的方法不断改进工具包对使用ML-Agent训练的所有模型的推理支持。 (有关所有ML-Agents功能的描述，请参见我们的GitHub ML-Agents概述页面。)我们已经亲眼目睹了这些改进如何实现了新的演示和环境(如Puppo)以及与真实游戏(如Jam City的Snoopy Pop和携带城堡的疯狂之源 。

Snoopy Pop (top-left), Puppo Day at the Races (top-right), and Source of Madness (bottom)

史努比流行音乐(左上)，Puppo Day at the Races(右上)和疯狂之源(下)

Specifically for AI researchers, we created the Obstacle Tower Environment and Challenge (built with ML-Agents) to serve as a benchmark for vision, control, and planning. We’ve also seen other researchers and labs adopt ML-Agents for creating research benchmarks. Prominent examples include the Arena multi-agent environments, the Animal AI Olympics, and the continuous control Marathon Environments.

我们专门为AI研究人员创建了障碍塔环境与挑战赛 (由ML-Agents构建)，以作为视觉，控制和规划的基准。 我们还看到其他研究人员和实验室采用ML-Agent创建研究基准。 突出的例子包括竞技场多主体环境， 动物AI奥运会和持续控制的马拉松环境 。

Obstacle Tower (top-left), Marathon Environments (top-right), Animal AI Olympics (bottom-left), and Arena (bottom-right)

障碍塔(左上)，马拉松环境(右上)，动物AI奥运会(左下)和竞技场(右下)

Since our initial release, the ML-Agents community grew from a loose confederation of AI researchers, game developers, and students to thousands of engaged community participants. This includes several creative demonstrations of ML-Agents that are shared online and directly with us. As a result, our GitHub repository has obtained over 8,400 stars and 2,300 forks, and our research paper Unity: A General Platform for Intelligent Agents was cited over 115 times.

自最初发布以来，ML-Agents社区已从AI研究人员，游戏开发人员和学生的松散联盟发展为成千上万的参与社区参与者。 其中包括在线与我们直接共享的ML-Agent的多个创意演示。 结果，我们的GitHub存储库获得了8,400多个星星和2,300个分支，我们的研究论文《 Unity：智能代理的通用平台》被引用了115次以上。

ML-Agents Unity软件包v1.0 (ML-Agents Unity Package v1.0)

Today, we’re delighted to announce that as of our latest release the ML-Agents Unity package is now at v1.0.0 and available as a Preview package in the Unity Package Manager. Our Unity: A General Platform for Intelligent Agents research paper has been updated to reflect ML-Agents Release 1.

今天，我们很高兴地宣布，自最新版本开始 ， ML-Agents Unity软件包现已发布于v1.0.0 ，可在Unity Package Manager中作为Preview软件包获得。 我们的《 Unity：智能代理的通用平台》研究论文已经更新，以反映ML-Agents版本1。

This version change is reflective of two core improvements to ML-Agents:

此版本更改反映了ML-Agent的两项核心改进：

1. API improvements. Several months ago, we began an overhaul to make our C# SDK much easier and more intuitive to use. The result was a number of major improvements that were phased in over several releases, starting from v0.10.0 in September 2019 and culminating in our latest release. More details on these changes can be found in our release notes.

   API的改进。 几个月前，我们开始进行大修，以使我们的C＃SDK更加容易使用。 结果是从2019年9月的v0.10.0开始逐步扩展到多个版本中的许多重大改进，最终达到了我们的最新版本。 有关这些更改的更多详细信息，请参见我们的发行说明 。

Starting with ML-Agents Release 1, each GitHub release will publish a new version for each of the packages that make up ML-Agents. With ML-Agents Release 1, we’ve set the following versions:

从ML-Agents版本1开始 ，每个GitHub版本都会为构成ML-Agents的每个软件包发布一个新版本。 在ML-Agents Release 1中，我们设置了以下版本：

• com.unity.ml-agents (v1.0.0, C#)

  com.unity.ml-agents( v1.0.0 ，C＃)

  com.unity.ml-agents (v1.0.0, C#)

  com.unity.ml-agents( v1.0.0 ，C＃)

• Communicator (v1.0.0, C#/Python)

  Communicator( v1.0.0 ，C＃/ Python)

  Communicator (v1.0.0, C#/Python)

  Communicator( v1.0.0 ，C＃/ Python)

• ml-agents, ml-agents-envs, gym-unity (v0.16.0, Python).

  ml-agents，ml-agents-envs，gym-unity( v0.16.0 ，Python)。

  ml-agents, ml-agents-envs, gym-unity (v0.16.0, Python).

  ml-agents，ml-agents-envs，gym-unity( v0.16.0 ，Python)。

More details on the versioning for our packages and corresponding changes to our GitHub releases can be found on the Versioning page.

有关我们软件包的版本控制以及对GitHub版本的相应更改的更多详细信息，可以在“ 版本控制”页面上找到。

下一步是什么？ (What’s next?)

ML-Agents Release 1 is the beginning of a very exciting journey. We plan to continue developing the toolkit by improving the performance and efficacy of our training algorithms, evolving our Unity package based on your feedback, and adding more example environments that are inspired by gaming and industrial applications of ML-Agents. You can keep up and provide input on our roadmap in the ML-Agents Forum.

ML-Agents Release 1是一段非常激动人心的旅程的开始。 我们计划通过改善培训算法的性能和功效，根据您的反馈改进Unity包以及添加更多受ML-Agent游戏和工业应用启发的示例环境，来继续开发该工具包。 您可以在ML-Agents论坛上跟进并提供我们的路线图。

In addition to evolving the core toolkit, we have a number of exciting improvements planned that we’ll now briefly overview.

除了发展核心工具包外，我们还计划了许多令人兴奋的改进，现在将简要概述。

已验证Unity 2020.2的软件包 (Verified package for Unity 2020.2)

Part of being a verified package in Unity is to provide peace of mind that the package will have undergone significant testing and have been verified to work safely with a specific version of Unity.  Meaning, if you want to use ML-Agents in a production game, we want to ensure we are supporting you. We are planning to release a Verified package for Unity 2020.2. This also means that we will be supporting the ML-Agents Unity package for the Unity 2020 LTS cycle.

在Unity中经过验证的软件包的一部分是让您放心，该软件包将经过大量测试，并且经过验证可在特定版本的Unity上安全地工作。 意思是，如果您想在生产游戏中使用ML-Agent，我们希望确保我们为您提供支持。 我们计划发布Unity 2020.2的经过验证的软件包。 这也意味着我们将为Unity 2020 LTS周期支持ML-Agents Unity软件包。

ML-Agents云 (ML-Agents Cloud)

Scale out your training with ML-Agents Cloud

使用ML-Agents Cloud扩展培训

One common piece of feedback we get from ML-Agents users is the desire for training without the need to install Python. We’ve also seen how restrictive it can be for our users to train on a local machine, limiting the number of environment and hyperparameter variations that can be trained at once. ML-Agents Cloud is a cloud offering we intend to launch later this year that will enable ML-Agents users to train on our scalable cloud infrastructure. Users will be able to submit many concurrent training sessions or easily scale out a training session across many machines for faster results.

我们从ML-Agents用户那里得到的一个常见反馈是，无需安装Python就可以进行培训。 我们还看到了对用户在本地计算机上进行培训的限制，从而限制了可以立即进行培训的环境和超参数变化的数量。 ML-Agents Cloud是我们计划在今年晚些时候推出的云产品，它将使ML-Agents用户能够在我们的可扩展云基础架构上进行培训。 用户将能够提交许多并发的培训课程，或者轻松地在多台机器上扩展培训课程，从而获得更快的结果。

Currently, we are opening up signups to be considered for early preview access to ML-Agents Cloud. If you are an existing ML-Agents user and need help with scaling and managing experiments, sign up here.

当前，我们正在开放注册，以考虑对ML-Agents Cloud进行早期预览访问。 如果您是ML-Agents的现有用户，并且需要扩展和管理实验的帮助，请在此处注册 。

DOTS世界中的ML代理商 (ML-Agents in a DOTS World)

演示地址

Unity’s core is being rebuilt with the Data-Oriented Technology Stack (DOTS). DOTS offers significant performance benefits by enabling builds to be smaller in size and run faster. These benefits are magnified in the context of simulations and machine learning. As such, we’ve been internally prototyping a version of ML-Agents that is built for DOTS. We’ve successfully integrated our DOTS prototype into sample scenes (see above) and Unity demos such as MegaCity and TinyRacing. The results have been outstanding. We were able to train agents in complex and large environments such as MegaCity in just a couple of hours on a standard laptop. We intend to release an experimental version of ML-Agents for DOTS later this year.

Unity的核心正在使用面向数据的技术堆栈( DOTS )进行重建。 DOTS通过使构建体尺寸更小，运行速度更快，可提供显着的性能优势。 这些优势在仿真和机器学习的背景下得到了放大。 因此，我们已经在内部为DOTS构建了ML-Agents版本。 我们已经成功地将DOTS原型集成到示例场景(见上文)和Unity演示中，例如MegaCity和TinyRacing 。 结果非常出色。 我们能够使用标准笔记本电脑在几个小时内对复杂的大型环境(例如MegaCity)进行培训。 我们打算在今年晚些时候为DOTS发布ML-Agent的实验版本。

演示地址

If your game or Unity project is being built using DOTS and you are interested in ML-Agents, please email us. We are looking for interested preview users to work with us on improving ML-Agents for DOTS.

如果您的游戏或Unity项目是使用DOTS构建的，并且您对ML-Agents感兴趣，请给我们发送电子邮件 。 我们正在寻找感兴趣的预览用户与我们合作，以改进DOTS的ML-Agent。

机器人技术 (Robotics)

演示地址

For our robotics researchers, Unity with NVIDIA PhysX 4.0 has dramatically improved the quality of robotics simulation (see Physics Update in Unity 2019.3). Unity 2020.1 includes a new articulation joint system powered by Nvidia’s PhysX 4.1, which offers a dramatic improvement in simulating robotic arms and continuous joints. It uses Featherstone’s algorithm, reduced coordinate representation, and a new non-linear iterative solver to drastically reduce unwanted stretch in the joints. In practice, this means that we can now chain many joints in a row and still achieve stable and precise movement.

对于我们的机器人研究人员而言，带有NVIDIA PhysX 4.0的 Unity大大提高了机器人仿真的质量(请参见Unity 2019.3中的Physics Update )。 Unity 2020.1包括一个由Nvidia的PhysX 4.1提供支持的新的关节关节系统 ，该系统在模拟机器人手臂和连续关节方面取得了巨大的进步。 它使用Featherstone的算法，减少的坐标表示以及新的非线性迭代求解器来大大减少关节中不需要的拉伸。 实际上，这意味着我们现在可以将许多关节连续链接在一起，并且仍然可以实现稳定而精确的运动。

You can already get started with the new articulation joint system in Unity 2020.1 (beta). Check out the Unity Robotics Demo project (integrated with ML-Agents Release 1) if you’d like to experiment with the robotics environment above or use it as a sample project to create your own robotics environments. Additionally, we plan to expand the example environments within ML-Agents to include additional robotics and continuous control environments.

您已经可以使用Unity 2020.1(测试版)中的新关节连接系统开始使用。 如果您想尝试上述机器人环境，或者将其用作创建您自己的机器人环境的示例项目，请查看Unity机器人演示项目 (与ML-Agents版本1集成)。 此外，我们计划在ML-Agents中扩展示例环境，以包括其他机器人技术和连续控制环境。

了解如何实施ML-Agents版本1 (Learn how to implement ML-Agents Release 1)

We’ve partnered with Immersive Limit to create ML-Agents: Hummingbirds, a course on the Unity Learn platform that teaches you how to implement ML-Agents Release 1 through exercises, code walkthroughs, and helpful discussions.

我们已经与Immersive Limit合作创建了ML-Agents：Hummingbirds ，这是Unity学习平台上的一门课程，教您如何通过练习，代码演练和有益的讨论来实现ML-Agents Release 1。

Learn how to train neural networks to perform a challenging task —  getting hummingbirds with six degrees of freedom and complicated flight paths to their flowers. By the end of this course, you’ll have a good understanding of how you can harness the power of ML-Agents Release 1 to create intelligent agents and integrate them into your own Unity games and simulation projects.

了解如何训练神经网络执行具有挑战性的任务-使蜂鸟具有六个自由度和复杂的飞行路径来开花。 在本课程结束时，您将对如何利用ML-Agents Release 1的功能创建智能代理并将它们集成到您自己的Unity游戏和模拟项目中有很好的了解。

谢谢！ (Thank you!)

On behalf of the entire Unity ML-Agents team, we want to thank you all for your continued support throughout the years and continuing on this journey with us!

我们谨代表整个Unity ML-Agents团队感谢您多年来的一如既往的支持，并继续与我们一起前进！

Unity ML-Agents team members. (Left to right, top to bottom): Jason Bowman, Jeffrey Shih, Andrew Cohen, Yuan Gao, Chris Elion, Arthur Juliani, Ervin Teng, Chris Goy, Anupam Bhatnagar, Jonathan Harper, Vincent-Pierre Berges, and Marwan Mattar. Missing from photo: Hunter Henry.

Unity ML-Agents团队成员。 (从左到右，从上到下)：Jason Bowman，Jeffrey Shih，Andrew Cohen，Yuan Gao，Chris Elion，Arthur Juliani，Ervin Teng，Chris Goy，Anupam Bhatnagar，Jonathan Harper，Vincent-Pierre Berges和Marwan Mattar。 照片缺少：Hunter Henry。

下一步 (Next Steps)

To get started with ML-Agents, check out our GitHub homepage.

要开始使用ML-Agents，请查看我们的GitHub主页 。

If you use any of the features provided in this release, we’d love to hear from you. For any feedback, general issues, or questions regarding ML-Agents, please reach out to us on the ML-Agents forums or feel free to email us directly. If you encounter any bugs, please reach out to us on the ML-Agents GitHub issues page.

如果您使用此版本中提供的任何功能，我们很乐意收到您的来信。 关于ML-Agent的任何反馈，一般性问题或疑问，请在ML-Agents论坛上与我们联系，或随时直接给我们发送电子邮件 。 如果您遇到任何错误，请在ML-Agents GitHub问题页面上与我们联系。

If you’d like to work on this exciting intersection of Machine Learning and Games, we are hiring for several positions; please apply!

如果您想在机器学习和游戏这个令人兴奋的交叉领域工作，我们正在招聘几个职位； 请申请 ！

翻译自: https://blogs.unity3d.com/2020/05/12/announcing-ml-agents-unity-package-v1-0/

ml-agents0.7