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:

Receives actions from the agent
Outputs observations resulting from the dynamic behavior of the environment model
Generates a reward measuring how well the action contributes to achieving the task

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

Functions

`rlPredefinedEnv`	Create a predefined reinforcement learning environment
`rlSimulinkEnv`	Create reinforcement learning environment using dynamic model implemented in Simulink
`createIntegratedEnv`	Create Simulink model for reinforcement learning, using reference model as environment
`validateEnvironment`	Validate custom reinforcement learning environment

`rlFiniteSetSpec`	Create discrete action or observation data specifications for reinforcement learning environments
`rlNumericSpec`	Create continuous action or observation data specifications for reinforcement learning environments
`getActionInfo`	Obtain action data specifications from reinforcement learning environment or agent
`getObservationInfo`	Obtain observation data specifications from reinforcement learning environment or agent
`bus2RLSpec`	Create reinforcement learning data specifications for elements of a Simulink bus

Reinforcement learning agent

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

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

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

Create a reinforcement learning Simulink environment that contains an RL Agent block in place of a controller for the water level in a tank.