MATLAB强化学习 PG 算法

采用 policy gradient 学习方法训练agent，并行训练的参数也需要调整

%% 读取环境

ccc

env = rlPredefinedEnv("CartPole-Discrete");

obsInfo = getObservationInfo(env);

numObservations = obsInfo.Dimension(1);

actInfo = getActionInfo(env);

rng(0)

%% 初始化agent

actorNetwork = [

imageInputLayer([numObservations 1 1],'Normalization','none','Name','state')

fullyConnectedLayer(2,'Name','action')];

actorOpts = rlRepresentationOptions('LearnRate',1e-2,'GradientThreshold',1);

actor = rlRepresentation(actorNetwork,obsInfo,actInfo,'Observation',{'state'},'Action',{'action'},actorOpts);

agent = rlPGAgent(actor);

%% 设置训练参数

trainOpts = rlTrainingOptions(...

'MaxEpisodes', 1000, ...

'MaxStepsPerEpisode', 200, ...

'Verbose', false, ...

'Plots','training-progress',...

'StopTrainingCriteria','AverageReward',...

'StopTrainingValue',195,...

'ScoreAveragingWindowLength',100);

plot(env)

%% 并行学习设置

trainOpts.UseParallel = true;

trainOpts.ParallelizationOptions.Mode = "async";

trainOpts.ParallelizationOptions.DataToSendFromWorkers = "Gradients";

trainOpts.ParallelizationOptions.StepsUntilDataIsSent = -1;

%% 训练

trainingStats = train(agent,env,trainOpts);

%% 结果展示

simOptions = rlSimulationOptions('MaxSteps',500);

experience = sim(env,agent,simOptions);

totalReward = sum(experience.Reward);