This is machine translation

Translated by Microsoft
Mouseover text to see original. Click the button below to return to the English version of the page.

Note: This page has been translated by MathWorks. Click here to see
To view all translated materials including this page, select Country from the country navigator on the bottom of this page.

Simulink Environments

Model reinforcement learning environment dynamics using Simulink® models

In a reinforcement learning scenario, the environment models the dynamics with which the agent interacts. The environment:

  1. Receives actions from the agent

  2. Outputs observations resulting from the dynamic behavior of the environment model

  3. Generates a reward measuring how well the action contributes to achieving the task

You can create predefined and custom environments using Simulinkmodels. For more information, see Create Simulink Environments for Reinforcement Learning.

Functions

expand all

rlPredefinedEnvCreate a predefined reinforcement learning environment
rlSimulinkEnvCreate a reinforcement learning environment using a dynamic model implemented in Simulink
createIntegratedEnvCreate Simulink model for reinforcement learning, using reference model as environment
validateEnvironmentValidate custom reinforcement learning environment
rlFiniteSetSpecCreate discrete action or observation data specifications for reinforcement learning environments
rlNumericSpecCreate continuous action or observation data specifications for reinforcement learning environments
getActionInfoObtain action data specifications from reinforcement learning environment or agent
getObservationInfoObtain observation data specifications from reinforcement learning environment or agent
bus2RLSpecCreate reinforcement learning data specifications for elements of a Simulink bus

Blocks

RL AgentReinforcement learning agent

Topics

Create Simulink Environments for Reinforcement Learning

Model environment dynamics using a Simulink model that interacts with the agent, generating rewards and observations in response to agent actions.

Define Reward Signals

Create a reward signal that measures how successful the agent is at achieving its goal.

Load Predefined Simulink Environments

You can train agents in environments for predefined Simulink models for which the actions, observations, rewards, and dynamics are already defined.