Implementation of Proximal Policy Optimisation

6 次查看（过去 30 天）
shoki kobayashi
shoki kobayashi 2020-9-11
评论： Muhammad Adeel 2024-8-22
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 个评论
Kashish Dhal
Kashish Dhal 2021-10-12
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?

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Emmanouil Tzorakoleftherakis
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 个评论
shoki kobayashi
shoki kobayashi 2020-9-24
I was able to operate successfully.
Thank you very much.
Muhammad Adeel
Muhammad Adeel 2024-8-22
Can you please provide the correct actor network code because I am facing the same error after many tries.

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Reinforcement Learning 的更多信息

标签

产品

Community Treasure Hunt

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

Start Hunting!

Translated by