Error encountered while creating actor representation:
Observation names must match the names of the deep neural network's input layers. Make sure all observation names appear in the neural network.
My code
% Clear workspace, command window, and close all figures
clear all; clc; close all;
% Define State and Action Dimensions
stateDim = 5; % State dimension
actionDim = 3; % Action dimension
% Create Observation and Action Specifications
ObservationInfo = rlNumericSpec([stateDim 1]);
ObservationInfo.Name = "state";
ActionInfo = rlNumericSpec([actionDim 1], 'LowerLimit', [-1; -1; -1], 'UpperLimit', [1; 1; 1]);
ActionInfo.Name = "action";
% Display the properties to ensure consistency
disp(ObservationInfo);
disp(ActionInfo);
% Create the environment with the step and reset functions
try
env = rlFunctionEnv(ObservationInfo, ActionInfo, @stepFunction, @resetFunction);
catch ME
disp('Error setting up environment:');
disp(ME.message);
return;
end
% Create a minimal critic network
criticNetwork = [
featureInputLayer(stateDim, 'Normalization', 'none', 'Name', 'state')
fullyConnectedLayer(1, 'Name', 'output')];
% Create a minimal actor network
actorNetwork = [
featureInputLayer(stateDim, 'Normalization', 'none', 'Name', 'state')
fullyConnectedLayer(actionDim, 'Name', 'output')];
% Display layer names for verification
disp(['Critic Network Input Layer Name: ', criticNetwork(1).Name]);
disp(['Actor Network Input Layer Name: ', actorNetwork(1).Name]);
% Attempt to create the actor and critic representations
try
critic = rlValueFunction(layerGraph(criticNetwork), ObservationInfo);
actor = rlStochasticActorRepresentation(layerGraph(actorNetwork), ObservationInfo, ActionInfo);
catch ME
disp('Error encountered while creating actor representation:');
disp(ME.message);
disp('Observation Info and Actor Network Input Layer Names:');
disp(['ObservationInfo Name: ', ObservationInfo.Name]);
disp(['Actor Network Input Layer Name: ', actorNetwork(1).Name]);
return; % Stop execution if there's a mismatch error
end
% Create the PPO agent and specify agent options
agentOptions = rlPPOAgentOptions('ClipFactor', 0.2, 'EntropyLossWeight', 0.01, ...
'SampleTime', 0.1, 'MiniBatchSize', 64, 'ExperienceHorizon', 128);
agent = rlPPOAgent(actor, critic, agentOptions);
% Specify training options and run training
trainOpts = rlTrainingOptions('MaxEpisodes', 1000, 'MaxStepsPerEpisode', 500, ...
'Verbose', true, 'Plots', 'training-progress', 'StopTrainingCriteria', 'AverageReward', ...
'StopTrainingValue', 500);
trainingStats = train(agent, env, trainOpts);
% Custom reset function to initialize the environment
function [initialObs, loggedSignals] = resetFunction()
stateDim = 5;
initialObs = randn(stateDim, 1);
loggedSignals.State = initialObs;
end
% Custom step function to define environment behavior
function [nextObs, reward, isDone, loggedSignals] = stepFunction(action, loggedSignals)
state = loggedSignals.State;
nextObs = state + [0.1 * action; zeros(2, 1)];
reward = -sum((nextObs(1:3) - action).^2);
isDone = any(abs(nextObs(1:3)) > 10);
loggedSignals.State = nextObs;
end
