env = rlPredefinedEnv("DoubleIntegrator-Discrete");
obsInfo = getObservationInfo(env);
numObservations = obsInfo.Dimension(1);
actInfo = getActionInfo(env);
numActions = numel(actInfo);

baselineNetwork = [
    imageInputLayer([numObservations 1 1], 'Normalization', 'none', 'Name', 'state')
    fullyConnectedLayer(8, 'Name', 'BaselineFC')
    reluLayer('Name', 'CriticRelu1')
    fullyConnectedLayer(1, 'Name', 'BaselineFC2', 'BiasLearnRateFactor', 0)];
baselineOpts = rlRepresentationOptions('LearnRate',5e-3,'GradientThreshold',1);
baseline = rlRepresentation(baselineNetwork,baselineOpts,'Observation',{'state'},obsInfo);

actorNetwork = [
    imageInputLayer([numObservations 1 1], 'Normalization', 'none', 'Name', 'state')
    fullyConnectedLayer(numActions, 'Name', 'action', 'BiasLearnRateFactor', 0)];
actorOpts = rlRepresentationOptions('LearnRate',5e-3,'GradientThreshold',1);
actor = rlRepresentation(actorNetwork,actorOpts,...
    'Observation',{'state'},obsInfo,'Action',{'action'},actInfo);

agentOpts = rlPGAgentOptions(...
    'UseBaseline',true, ...
    'DiscountFactor', 0.99);
agent = rlPGAgent(actor,baseline,agentOpts);