Implementation of Proximal Policy Optimisation
14 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
shoki kobayashi
el 11 de Sept. de 2020
Comentada: Muhammad Adeel
el 22 de Ag. de 2024 a las 10:52
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';
open_system(mdl)
Ts = 0.05;
Tf = 20;
mdl = 'fivelinkrl';
open_system(mdl)
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);
%createPPOAgent
criticLayerSizes = [400 300];
actorLayerSizes = [400 300];
createNetworkWeights;
criticNetwork = [imageInputLayer([numObs 1 1],'Normalization','none','Name','observations')
fullyConnectedLayer(criticLayerSizes(1),'Name','CriticFC1', ...
'Weights',weights.criticFC1, ...
'Bias',bias.criticFC1)
reluLayer('Name','CriticRelu1')
fullyConnectedLayer(criticLayerSizes(2),'Name','CriticFC2', ...
'Weights',weights.criticFC2, ...
'Bias',bias.criticFC2)
reluLayer('Name','CriticRelu2')
fullyConnectedLayer(1,'Name','CriticOutput',...
'Weights',weights.criticOut,...
'Bias',bias.criticOut)];
criticOpts = rlRepresentationOptions('LearnRate',1e-3);
critic = rlValueRepresentation(criticNetwork,env.getObservationInfo, ...
'Observation',{'observations'},criticOpts);
actorNetwork = [imageInputLayer([numObs 1 1],'Normalization','none','Name','observations')
fullyConnectedLayer(actorLayerSizes(1),'Name','ActorFC1',...
'Weights',weights.actorFC1,...
'Bias',bias.actorFC1)
reluLayer('Name','ActorRelu1')
fullyConnectedLayer(actorLayerSizes(2),'Name','ActorFC2',...
'Weights',weights.actorFC2,...
'Bias',bias.actorFC2)
reluLayer('Name','ActorRelu2')
fullyConnectedLayer(numAct,'Name','Action',...
'Weights',weights.actorOut,...
'Bias',bias.actorOut)
softmaxLayer('Name','actionProbability')
];
actorOptions = rlRepresentationOptions('LearnRate',1e-3);
%%%% ↓error %%%%%%%%%%%%%%%%%
actor = rlStochasticActorRepresentation(actorNetwork,obsInfo,actInfo,...
'Observation',{'observations'}, actorOptions);
%%%% ↑error %%%%%%%%%%%%%%%%%%
opt = rlPPOAgentOptions('ExperienceHorizon',512,...
'ClipFactor',0.2,...
'EntropyLossWeight',0.02,...
'MiniBatchSize',64,...
'NumEpoch',3,...
'AdvantageEstimateMethod','gae',...
'GAEFactor',0.95,...
'SampleTime',0.05,...
'DiscountFactor',0.9995);
agent = rlPPOAgent(actor,critic,opt);
%TrainAgent
maxEpisodes = 4000;
maxSteps = floor(Tf/Ts);
trainOpts = rlTrainingOptions(...
'MaxEpisodes',maxEpisodes,...
'MaxStepsPerEpisode',maxSteps,...
'ScoreAveragingWindowLength',250,...
'Verbose',false,...
'Plots','training-progress',...
'StopTrainingCriteria','EpisodeCount',...
'StopTrainingValue',maxEpisodes,...
'SaveAgentCriteria','EpisodeCount',...
'SaveAgentValue',maxEpisodes);
trainingStats = train(agent,env,trainOpts);
save('agent.mat', 'agent')
Result in simulation
simOptions = rlSimulationOptions('MaxSteps',maxSteps);
experience = sim(env,agent,simOptions);
1 comentario
Kashish Dhal
el 12 de Oct. de 2021
Can you please update the correct code for the actor Network in the post, I am getting the same error and unable to follow through the comments?
Respuesta aceptada
Emmanouil Tzorakoleftherakis
el 15 de Sept. de 2020
Hello,
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
2 comentarios
Muhammad Adeel
el 22 de Ag. de 2024 a las 10:52
Can you please provide the correct actor network code because I am facing the same error after many tries.
Más respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!