getActionInfo

Obtain action data specifications from reinforcement learning environment, agent, or experience buffer

Syntax

actInfo = getActionInfo(env)

actInfo = getActionInfo(agent)

actInfo = getActionInfo(buffer)

Description

actInfo = getActionInfo(env) extracts action information from reinforcement learning environment env.

actInfo = getActionInfo(agent) extracts action information from reinforcement learning agent agent.

actInfo = getActionInfo(buffer) extracts action information from experience buffer buffer.

Examples

Extract Action and Observation Specifications from Reinforcement Learning Environment

The reinforcement learning environment for this example is a longitudinal dynamics model comprising two cars, a leader and a follower. The vehicle model is also used in the Adaptive Cruise Control System Using Model Predictive Control (Model Predictive Control Toolbox) example.

Open the model.

mdl = "rlACCMdl";
open_system(mdl);

Specify path to the agent block in the model.

agentblk = mdl + "/RL Agent";

Create the observation and action specifications.

% Observation specifications
obsInfo = rlNumericSpec([3 1],LowerLimit=-inf*ones(3,1),UpperLimit=inf*ones(3,1));
obsInfo.Name = "observations";
obsInfo.Description = "information on velocity error and ego velocity";

% Action specifications
actInfo = rlNumericSpec([1 1],LowerLimit=-3,UpperLimit=2);
actInfo.Name = "acceleration";

Define environment interface.

env = rlSimulinkEnv(mdl,agentblk,obsInfo,actInfo)

env = 
SimulinkEnvWithAgent with properties:

           Model : rlACCMdl
      AgentBlock : rlACCMdl/RL Agent
        ResetFcn : []
  UseFastRestart : on

The reinforcement learning environment env is a SimulinkEnvWithAgent object.

Extract the action and observation specifications from env.

actInfoExt = getActionInfo(env)

actInfoExt = 
  rlNumericSpec with properties:

     LowerLimit: -3
     UpperLimit: 2
           Name: "acceleration"
    Description: [0x0 string]
      Dimension: [1 1]
       DataType: "double"

obsInfoExt = getObservationInfo(env)

obsInfoExt = 
  rlNumericSpec with properties:

     LowerLimit: [3x1 double]
     UpperLimit: [3x1 double]
           Name: "observations"
    Description: "information on velocity error and ego velocity"
      Dimension: [3 1]
       DataType: "double"

The action information contains acceleration values while the observation information contains the velocity and velocity error values of the ego vehicle.

Input Arguments

env — Reinforcement learning environment

rlFunctionEnv object | SimulinkEnvWithAgent object | rlNeuralNetworkEnvironment object | predefined MATLAB environment object

Reinforcement learning environment from which to extract the action information, specified as one of the following:

• MATLAB^® environment represented as one of the following objects.

  • rlFunctionEnv

  • rlNeuralNetworkEnvironment

  • Predefined MATLAB environment created using rlPredefinedEnv

• Simulink^® environment represented as a SimulinkEnvWithAgent object.

For more information on reinforcement learning environments, see Reinforcement Learning Environments and Create Custom Simulink Environments.

agent — Reinforcement learning agent

rlQAgent object | rlSARSAAgent object | rlDQNAgent object | rlPGAgent object | rlDDPGAgent object | rlTD3Agent object | rlACAgent object | rlPPOAgent object | rlTRPOAgent object | rlSACAgent object | rlMBPOAgent object

Reinforcement learning agent from which to extract the action information, specified as one of the following objects.

• rlQAgent

• rlSARSAAgent

• rlDQNAgent

• rlDDPGAgent

• rlTD3Agent

• rlPGAgent

• rlACAgent

• rlPPOAgent

• rlTRPOAgent

• rlSACAgent

• rlMBPOAgent

For more information on reinforcement learning agents, see Reinforcement Learning Agents.

buffer — Experience buffer

rlReplayMemory object | rlPrioritizedReplayMemory object | rlHindsightReplayMemory object | rlHindsightPrioritizedReplayMemory object

Experience buffer, specified as one of the following replay memory objects.

• rlReplayMemory

• rlPrioritizedReplayMemory

• rlHindsightReplayMemory

• rlHindsightPrioritizedReplayMemory

Output Arguments

actInfo — Action specification

rlNumericSpec object | rlFiniteSetSpec object | vector containing one rlFiniteSetSpec followed by one rlNumericSpec object

Action specification, returned as one of the following:

• One rlNumericSpec object (for continuous action spaces)

• One rlFiniteSetSpec object (for discrete action spaces)

• A vector consisting of one rlFiniteSetSpec followed by one rlNumericSpec object (for hybrid action spaces)

The action specification defines the properties of the environment action channel, such as its dimensions, data type, and name.

Note

For non-hybrid action spaces (either discrete or continuous) or only one action channel is allowed. Environments with hybrid action spaces have two action channels, the first one for the discrete part of the action, the second one for the continuous part of the action.

The action specifications object defines the properties of the environment action channel, such as its dimensions, data type, and name.

Version History

Introduced in R2019a