teena_singh asked . 2021-05-25

"Unable to evaluate the loss function. Check the loss function and ensure it

clear
    close all
    
    %% Model parameters
    T_init = 0;
    T_final = 100;
    dt = 1;
    
    rng("shuffle")
    
    baseEnv = baseEnvironment();
    p1_pos = randi(baseEnv.L,1);
    p2_pos = randi(baseEnv.L,1);
    while p1_pos == p2_pos
        p2_pos = randi(baseEnv.L,1);
    end
 
    rng("shuffle")
    
    baseEnv = baseEnvironment();
    % validateEnvironment(baseEnv)
    p1_pos = randi(baseEnv.L,1);
    p2_pos = randi(baseEnv.L,1);
    while p1_pos == p2_pos
        p2_pos = randi(baseEnv.L,1);
    end
    
    agent1 = IMAgent(baseEnv, p1_pos, 1, 'o');
    agent2 = IMAgent(baseEnv, p2_pos, 2, 'x');
    listOfAgents = [agent1; agent2];
    multiAgentEnv = multiAgentEnvironment(listOfAgents);
    
    %
    actInfo = getActionInfo(baseEnv);
    obsInfo = getObservationInfo(baseEnv);
    
    %%build the agent1
    actorNetwork = [imageInputLayer([obsInfo.Dimension(1) 1 1],'Normalization','none','Name','state')
                    fullyConnectedLayer(24,'Name','fc1')
                    reluLayer('Name','relu1')
                    fullyConnectedLayer(24,'Name','fc2')
                    reluLayer('Name','relu2')
                    fullyConnectedLayer(numel(actInfo.Elements),'Name','output')
                    softmaxLayer('Name','actionProb')];
    actorOpts = rlRepresentationOptions('LearnRate',1e-3,'GradientThreshold',1);
    actor = rlStochasticActorRepresentation(actorNetwork,...
        obsInfo,actInfo,'Observation','state',actorOpts);
    actor = setLoss(actor, @actorLossFunction);
    %obj.brain = rlPGAgent(actor,baseline,agentOpts);
    agentOpts = rlPGAgentOptions('UseBaseline',false, 'DiscountFactor', 0.99);
    agent1.brain = rlPGAgent(actor,agentOpts);
    %%build the agent2
    actorNetwork = [imageInputLayer([obsInfo.Dimension(1) 1 1],'Normalization','none','Name','state')
                    fullyConnectedLayer(24,'Name','fc1')
                    reluLayer('Name','relu1')
                    fullyConnectedLayer(24,'Name','fc2')
                    reluLayer('Name','relu2')
                    fullyConnectedLayer(numel(actInfo.Elements),'Name','output')
                    softmaxLayer('Name','actionProb')];
    actorOpts = rlRepresentationOptions('LearnRate',1e-3,'GradientThreshold',1);
    actor = rlStochasticActorRepresentation(actorNetwork,...
        obsInfo,actInfo,'Observation','state',actorOpts);
    actor = setLoss(actor, @actorLossFunction);
    %obj.brain = rlPGAgent(actor,baseline,agentOpts);
    agentOpts = rlPGAgentOptions('UseBaseline',false, 'DiscountFactor', 0.99);
    agent2.brain = rlPGAgent(actor,agentOpts);
    %%
    
    averageGrad = [];
    averageSqGrad = [];
    learnRate = 0.05;
    gradDecay = 0.75;
    sqGradDecay = 0.95;
    numOfEpochs = 1;
    
    numEpisodes = 5000;
    maxStepsPerEpisode = 250;
    discountFactor = 0.995;
    aveWindowSize = 100;
    trainingTerminationValue = 220;
    
    
    
    loss_history = [];
    for i = 1:numOfEpochs
        action_hist = [];
        reward_hist = [];
        observation_hist = [multiAgentEnv.baseEnv.state];
        for t = T_init:1:T_final
            actionList = multiAgentEnv.act();
            [observation, reward, multiAgentEnv.isDone, ~] = multiAgentEnv.step(actionList);
    
            if t == T_final
                multiAgentEnv.isDone = true;
            end
            
            action_hist = cat(3, action_hist, actionList);
            reward_hist = cat(3, reward_hist, reward);
            if multiAgentEnv.isDone == true
                break
            else
                observation_hist = cat(3, observation_hist, observation);
            end
        end
        if size(observation_hist,3) ~= size(action_hist,3)
            print("gi")
        end
        clear observation reward
        actor = getActor(agent1.brain);        
        batchSize = min(t,maxStepsPerEpisode);
    
        observations = observation_hist;
        actions = action_hist(1,:,:);
        rewards = reward_hist(1,:,:);
        
        observationBatch = permute(observations(:,:,1:batchSize), [2,1,3]);
        actionBatch = actions(:,:,1:batchSize);
        rewardBatch = rewards(:,1:batchSize);
        
        
        discountedReturn = zeros(1,int32(batchSize));
        for t = 1:batchSize
            G = 0;
            for k = t:batchSize
                G = G + discountFactor ^ (k-t) * rewardBatch(k);
            end
            discountedReturn(t) = G;
        end
        
        lossData.batchSize = batchSize;
        lossData.actInfo = actInfo;
        lossData.actionBatch = actionBatch;
        lossData.discountedReturn = discountedReturn;
        
        % 6. Compute the gradient of the loss with respect to the policy
        % parameters.
        actorGradient = gradient(actor,'loss-parameters', {observationBatch},lossData);
        
        
        p1_pos = randi(baseEnv.L,1);
        p2_pos = randi(baseEnv.L,1);
        while p1_pos == p2_pos
            p2_pos = randi(baseEnv.L,1);
        end
        multiAgentEnv.reset([p1_pos; p2_pos]);
    end
    
    
    function loss = actorLossFunction(policy, lossData)
    
        % Create the action indication matrix.
        batchSize = lossData.batchSize;
        Z = repmat(lossData.actInfo.Elements',1,batchSize);
        actionIndicationMatrix = lossData.actionBatch(:,:) == Z;
    
        % Resize the discounted return to the size of policy.
        G = actionIndicationMatrix .* lossData.discountedReturn;
        G = reshape(G,size(policy));
    
        % Round any policy values less than eps to eps.
        policy(policy < eps) = eps;
    
        % Compute the loss.
        loss = -sum(G .* log(policy),'all');
    end

When I run the code, I am getting the following error:

Error using rl.representation.rlAbstractRepresentation/gradient (line 181)
Unable to compute gradient from representation.

Error in main1 (line 154)
    actorGradient = gradient(actor,'loss-parameters', {observationBatch},lossData);

Caused by:
    Unable to evaluate the loss function. Check the loss function and ensure it runs successfully.
        Reference to non-existent field 'Advantage'.

I also tried running the example in the link; it works, but not my code. I put a breakpoint the loss function, but it isn't called during the gradient calculation, and from the error message, I suspect this is the problem, but the thing is it works when I run the code of the example in mathworks' website.

deep learning , matlab , simulink ,