MathWorks - Mobile View
  • 碻形冰暨硞 MathWorks 帐憷碻形冰暨硞 MathWorks 帐憷
  • Access your MathWorks Account
    • 我的帐户
    • 我的社区资料
    • 关联许可证
    • 登出
  • 产品
  • 解决方案
  • 学术
  • 支持
  • 社区
  • 活动
  • 获取 MATLAB
MathWorks
  • 产品
  • 解决方案
  • 学术
  • 支持
  • 社区
  • 活动
  • 获取 MATLAB
  • 碻形冰暨硞 MathWorks 帐憷碻形冰暨硞 MathWorks 帐憷
  • Access your MathWorks Account
    • 我的帐户
    • 我的社区资料
    • 关联许可证
    • 登出

视频与网上研讨会

  • MathWorks
  • 视频
  • 视频首页
  • 搜索
  • 视频首页
  • 搜索
  • 联系销售
  • 试用软件
  Register to watch video
  • Description
  • Full Transcript
  • Related Resources

What Is Reinforcement Learning Toolbox?

Emmanouil Tzorakoleftherakis, MathWorks

Reinforcement Learning Toolbox™ provides MATLAB® functions and Simulink® blocks for training policies using reinforcement learning algorithms including DQN, A2C, and DDPG. The toolbox lets you implement controllers and decision-making systems for complex applications such as robotics, self-driving cars, and more.

You can represent policies and value functions using deep neural networks, polynomials, or lookup tables. Train policies by enabling reinforcement learning agents to interact with environments created in MATLAB or Simulink. Evaluate built-in and custom algorithms, experiment with hyperparameter settings, and monitor training progress. Accelerate training by parallelizing simulations and calculations on multicore CPUs, GPUs, computer clusters, and cloud resources (with Parallel Computing Toolbox™ and MATLAB Parallel Server™).

You can import existing policies from deep learning frameworks such as TensorFlow™ Keras and PyTorch through the ONNX™ model format (with Deep Learning Toolbox™). Generate optimized C, C++, and CUDA code to deploy trained policies on embedded platforms. The toolbox includes reference examples for using reinforcement learning to design controllers for robotics and automated driving applications.

Reinforcement Learning Toolbox provides functions and blocks that let you implement controllers and decision-making algorithms for autonomous systems such as robots and self-driving cars.

The toolbox enables you to work through all steps of the reinforcement learning workflow, from creating the environment and the agent to policy training and deployment, with MATLAB and Simulink.

Create deep neural network policies and value functions with Deep Network Designer or programmatically with built-in functions.

In addition to neural networks, polynomials and lookup tables are also supported.

Define an agent by combining the policy with built-in training algorithms, such as actor-critic methods or Deep Q network.

You can create environments in both MATLAB and Simulink.

In Simulink, create a model that describes the environment dynamics and reward signal.

Use the Agent block to interface the environment model with the agent.

For MATLAB environments, you may start with provided templates and make modifications as needed.

You can also select from several predefined MATLAB and Simulink environments.

To train an agent, specify training options such as stopping criteria and start the training process using the agent and the environment model.

Parallel Computing Toolbox and MATLAB Parallel Server let you accelerate training by parallelizing simulations and calculations.

During training, the Episode manager helps you visually monitor the training progress and provides summary statistics.

After training is complete, you can verify the trained agent with the simulation environment and you can generate CUDA and C/C++ code to deploy the trained policy.

For more information on Reinforcement Learning Toolbox, please refer to the documentation and provided examples.

Get started with a free trial of Reinforcement Learning Toolbox today.

Related Products

  • Reinforcement Learning Toolbox
  • Deep Learning Toolbox
Related Information
Download ebook: Reinforcement Learning with MATLAB and Simulink

Feedback

Featured Product

Reinforcement Learning Toolbox

  • Request Trial
  • Get Pricing

Up Next:

35:00
Hands-on Learning with MATLAB and Analog Discovery

Related Videos:

45:19
Enabling Project-Based Learning with MATLAB, Simulink, and...
42:22
Enabling Project-Based Learning with MATLAB and Simulink
30:30
Teaching Physics with MATLAB Through Project-Based Learning
42:45
Signal Processing and Machine Learning Techniques for...

View more related videos

MathWorks - Domain Selector

Select a Web Site

Choose a web site to get translated content where available and see local events and offers. Based on your location, we recommend that you select: .

Select web site

You can also select a web site from the following list:

How to Get Best Site Performance

Select the China site (in Chinese or English) for best site performance. Other MathWorks country sites are not optimized for visits from your location.

Americas

  • América Latina (Español)
  • Canada (English)
  • United States (English)

Europe

  • Belgium (English)
  • Denmark (English)
  • Deutschland (Deutsch)
  • España (Español)
  • Finland (English)
  • France (Français)
  • Ireland (English)
  • Italia (Italiano)
  • Luxembourg (English)
  • Netherlands (English)
  • Norway (English)
  • Österreich (Deutsch)
  • Portugal (English)
  • Sweden (English)
  • Switzerland
    • Deutsch
    • English
    • Français
  • United Kingdom (English)

Asia Pacific

  • Australia (English)
  • India (English)
  • New Zealand (English)
  • 中国
    • 简体中文Chinese
    • English
  • 日本Japanese (日本語)
  • 한국Korean (한국어)

Contact your local office

  • 联系销售
  • 试用软件

了解产品

  • MATLAB
  • Simulink
  • 学生版软件
  • 硬件支持
  • 文件交换

试用或购买

  • 下载
  • 试用软件
  • 联系销售
  • 定价和许可
  • 如何购买

如何使用

  • 文档
  • 教程
  • 示例
  • 视频与网上研讨会
  • 培训

获取支持

  • 安装帮助
  • MATLAB 问答社区
  • 咨询
  • 许可中心
  • 联系支持

关于 MathWorks

  • 招聘
  • 新闻室
  • 社会愿景
  • 联系销售
  • 关于 MathWorks

MathWorks

Accelerating the pace of engineering and science

MathWorks 公司是世界领先的为工程师和科学家提供数学计算软件的开发商。

发现…

  • Select a Web Site United States
  • 专利
  • 商标
  • 隐私权政策
  • 防盗版
  • 应用状态

京ICP备12052471号

© 1994-2021 The MathWorks, Inc.

  • Facebook
  • Twitter
  • Weibo
  • WeChat

    WeChat

  • LinkedIn
  • RSS

关注我们