Create金宝appEnvironments for Reinforcement Learning Designer

When training an agent using theReinforcement Learning Designerapp, you can create a predefined Simulink^®environment from within the app or import a custom environment.

To create a predefined environment, on theReinforcement Learningtab, in theEnvironmentsection, clickNew. Then, underSimulink Environments, select one of the predefined environments.

To use a custom environment, you must first create the environment at the MATLAB^®command line and then import the environment intoReinforcement Learning Designer. For more information on creating a Simulink environment, seeCreate Simulink Reinforcement Learning Environments.

For training and simulating Simulink environments, you must define all variables necessary for running the Simulink mode in the MATLAB workspace.

Once you create a custom environment using one of the methods described in the preceding section, import the environment intoReinforcement Learning Designer. On theReinforcement Learningtab, click进口. Then, underSelect Environment, select the environment.

Once you have created or imported an environment, the app adds the environment to theEnvironmentspane.

Once you have created an environment, you can create an agent to train in that environment. For more information, seeCreate Agents Using Reinforcement Learning Designer.

See Also

Reinforcement Learning Designer

Related Topics

• Create Simulink Reinforcement Learning Environments
• Create MATLAB Environments for Reinforcement Learning Designer
• Create Agents Using Reinforcement Learning Designer
• Design and Train Agent Using Reinforcement Learning Designer