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

statePath = imageInputLayer([numObservations 1 1], 'Normalization', 'none', 'Name', 'state');
actionPath = imageInputLayer([numActions 1 1], 'Normalization', 'none', 'Name', 'action');
commonPath = [concatenationLayer(1,2,'Name','concat')
             quadraticLayer('Name','quadratic')
             fullyConnectedLayer(1,'Name','StateValue','BiasLearnRateFactor', 0, 'Bias', 0)];
criticNetwork = layerGraph(statePath);
criticNetwork = addLayers(criticNetwork, actionPath);
criticNetwork = addLayers(criticNetwork, commonPath);
criticNetwork = connectLayers(criticNetwork,'state','concat/in1');
criticNetwork = connectLayers(criticNetwork,'action','concat/in2');
criticOpts = rlRepresentationOptions('LearnRate',5e-3,'GradientThreshold',1);
critic = rlRepresentation(criticNetwork,obsInfo,actInfo,...
    'Observation',{'state'},'Action',{'action'},criticOpts);

actorNetwork = [
    imageInputLayer([numObservations 1 1], 'Normalization', 'none', 'Name', 'state')
    fullyConnectedLayer(numActions, 'Name', 'action', 'BiasLearnRateFactor', 0, 'Bias', 0)];
actorOpts = rlRepresentationOptions('LearnRate',1e-04,'GradientThreshold',1);
actor = rlRepresentation(actorNetwork,obsInfo,actInfo,...
    'Observation',{'state'},'Action',{'action'},actorOpts);

agentOpts = rlDDPGAgentOptions(...
    'SampleTime',env.Ts,...
    'TargetSmoothFactor',1e-3,...
    'ExperienceBufferLength',1e6,...
    'DiscountFactor',0.99,...
    'MiniBatchSize',32);
agent = rlDDPGAgent(actor,critic,agentOpts);