MATLAB Answers

Implementation of Proximal Policy Optimisation

18 views (last 30 days)
I am currently trying to control the simlink homebrew environment using PPOAgent.
However, the following error occurs, and the problem continues to be unsuccessful.
How should we improve the situation?
Error: rl.representation.rlStochasticActorRepresentation (line 32)
Number of outputs for a continuous stochastic actor representation must be two times the number of actions.
Error: rlStochasticActorRepresentation (line 139)
Rep = rl.representation.rlStochasticActorRepresentation(...
my code
clear all
motion_time_constant = 0.01;
mdl = 'fivelinkrl';
Ts = 0.05;
Tf = 20;
mdl = 'fivelinkrl';
agentblk = [mdl '/RL Agent'];
numObs = 15;
obsInfo = rlNumericSpec([numObs 1]);
obsInfo.Name = 'observations';
numAct = 5;
actInfo = rlNumericSpec([numAct 1],'LowerLimit',-10,'UpperLimit',10);
actInfo.Name = 'Action';
% define environment
env = rlSimulinkEnv(mdl,agentblk,obsInfo,actInfo);
criticLayerSizes = [400 300];
actorLayerSizes = [400 300];
criticNetwork = [imageInputLayer([numObs 1 1],'Normalization','none','Name','observations')
fullyConnectedLayer(criticLayerSizes(1),'Name','CriticFC1', ...
'Weights',weights.criticFC1, ...
fullyConnectedLayer(criticLayerSizes(2),'Name','CriticFC2', ...
'Weights',weights.criticFC2, ...
criticOpts = rlRepresentationOptions('LearnRate',1e-3);
critic = rlValueRepresentation(criticNetwork,env.getObservationInfo, ...
actorNetwork = [imageInputLayer([numObs 1 1],'Normalization','none','Name','observations')
actorOptions = rlRepresentationOptions('LearnRate',1e-3);
%%%% ↓error %%%%%%%%%%%%%%%%%
actor = rlStochasticActorRepresentation(actorNetwork,obsInfo,actInfo,...
'Observation',{'observations'}, actorOptions);
%%%% ↑error %%%%%%%%%%%%%%%%%%
opt = rlPPOAgentOptions('ExperienceHorizon',512,...
agent = rlPPOAgent(actor,critic,opt);
maxEpisodes = 4000;
maxSteps = floor(Tf/Ts);
trainOpts = rlTrainingOptions(...
trainingStats = train(agent,env,trainOpts);
save('agent.mat', 'agent')
Result in simulation
simOptions = rlSimulationOptions('MaxSteps',maxSteps);
experience = sim(env,agent,simOptions);

Accepted Answer

Emmanouil Tzorakoleftherakis
It seems you want to use PPO with continuous action space. If that's the case, your actor network does not have the right architecture. With stochastic agents, the neural network should end with a path that outputs 'mean' value and another path that outputs 'variance'. In your case you seem to only have a single path. Please refer to this example here to get an idea on how to set up your actor network. Also make sure you are using 20a (PPO for continuous actions was not available in previous releases as far as I remember).
Hope that helps
  1 Comment
shoki kobayashi
shoki kobayashi on 24 Sep 2020
I was able to operate successfully.
Thank you very much.

Sign in to comment.

More Answers (0)

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!