基于DDPG算法的双有源全桥dcdc变换器调制策略问题

open_system('SPSDAB')
obsInfo = rlNumericSpec([3 1],...
    'LowerLimit',[-inf -inf 0  ]',...
    'UpperLimit',[ inf  inf inf]');
obsInfo.Name = 'observations';
obsInfo.Description = 'integrated error, error, and measured height';
numObservations = obsInfo.Dimension(1);

actInfo = rlNumericSpec([1 1]);
actInfo.Name = 'Transfer ratio';
numActions = actInfo.Dimension(1);
env = rlSimulinkEnv('SPSDAB','SPSDAB/RL Agent',...
    obsInfo,actInfo);
env.ResetFcn = @(in)localResetFcn(in);
Ts = 1.0;
Tf = 200;
rng(0)
statePath = [
    featureInputLayer(numObservations,'Normalization','none','Name','State')
    fullyConnectedLayer(50,'Name','CriticStateFC1')
    reluLayer('Name','CriticRelu1')
    fullyConnectedLayer(25,'Name','CriticStateFC2')];
actionPath = [
    featureInputLayer(numActions,'Normalization','none','Name','Action')
    fullyConnectedLayer(25,'Name','CriticActionFC1')];
commonPath = [
    additionLayer(2,'Name','add')
    reluLayer('Name','CriticCommonRelu')
    fullyConnectedLayer(1,'Name','CriticOutput')];

criticNetwork = layerGraph();
criticNetwork = addLayers(criticNetwork,statePath);
criticNetwork = addLayers(criticNetwork,actionPath);
criticNetwork = addLayers(criticNetwork,commonPath);
criticNetwork = connectLayers(criticNetwork,'CriticStateFC2','add/in1');
criticNetwork = connectLayers(criticNetwork,'CriticActionFC1','add/in2');


criticOpts = rlRepresentationOptions('LearnRate',1e-03,'GradientThreshold',1);
critic = rlQValueRepresentation(criticNetwork,obsInfo,actInfo,'Observation',{'State'},'Action',{'Action'},criticOpts);
actorNetwork = [
    featureInputLayer(numObservations,'Normalization','none','Name','State')
    fullyConnectedLayer(3, 'Name','actorFC')
    tanhLayer('Name','actorTanh')
    fullyConnectedLayer(numActions,'Name','Action')
    ];

actorOptions = rlRepresentationOptions('LearnRate',1e-04,'GradientThreshold',1);

actor = rlDeterministicActorRepresentation(actorNetwork,obsInfo,actInfo,'Observation',{'State'},'Action',{'Action'},actorOptions);
agentOpts = rlDDPGAgentOptions(...
    'SampleTime',Ts,...
    'TargetSmoothFactor',1e-3,...
    'DiscountFactor',1.0, ...
    'MiniBatchSize',64, ...
    'ExperienceBufferLength',1e6); 
agentOpts.NoiseOptions.Variance = 0.3;
agentOpts.NoiseOptions.VarianceDecayRate = 1e-5;
agent = rlDDPGAgent(actor,critic,agentOpts);
maxepisodes = 5000;
maxsteps = ceil(Tf/Ts);
trainOpts = rlTrainingOptions(...
    'MaxEpisodes',maxepisodes, ...
    'MaxStepsPerEpisode',maxsteps, ...
    'ScoreAveragingWindowLength',20, ...
    'Verbose',false, ...
    'Plots','training-progress',...
    'StopTrainingCriteria','AverageReward',...
    'StopTrainingValue',800);
doTraining = false;

if doTraining
    % Train the agent.
    trainingStats = train(agent,env,trainOpts);
else
    % Load the pretrained agent for the example.
    load('SPSDABDDPG.mat','agent')
end

代码是这样的，运行图如下

动作不发生变化不知道是为什么，有没有大佬帮忙看看这是为什么？