Timestep problems using Reinforcement Learning with EnergyPlus

Question

Emre Karakoc 2020-10-24

1
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/624848-timestep-problems-using-reinforcement-learning-with-energyplus

评论： Rezky Nanda 2022-4-21

I am currently trying to train an agent using an EnergyPlus Model.

Herefore I set up a Simulink Environment with observation, reward, agent and EnergyPlus Simulation block. The model and the EnergyPlus Simulation starts to run but then suddenly stops with error messages (code below). Does anyone have an idea how to solve this issue or where I should look for to find a solution?

Another question I have is regarding the agent and EnergyPlus. I want the agent to give me a value between 0 and 1. I want to use this value to simulate 1 hour in EnergyPlus. The agent should not output any values until I have the results(observations) of the first simulated hour. How do I have to set this up?

Error using rl.env.AbstractEnv/simWithPolicy (line 70)
An error occurred while simulating "KleinesModellSimulinka" with the agent "agent".
Error in rl.task.SeriesTrainTask/runImpl (line 33)
            [varargout{1},varargout{2}] = simWithPolicy(this.Env,this.Agent,simOpts);
Error in rl.task.Task/run (line 21)
            [varargout{1:nargout}] = runImpl(this);
Error in rl.task.TaskSpec/internal_run (line 159)
            [varargout{1:nargout}] = run(task);
Error in rl.task.TaskSpec/runDirect (line 163)
            [this.Outputs{1:getNumOutputs(this)}] = internal_run(this);
Error in rl.task.TaskSpec/runScalarTask (line 187)
                runDirect(this);
Error in rl.task.TaskSpec/run (line 69)
                runScalarTask(task);
Error in rl.train.SeriesTrainer/run (line 24)
            run(seriestaskspec);
Error in rl.train.TrainingManager/train (line 291)
            run(trainer);
Error in rl.train.TrainingManager/run (line 160)
            train(this);
Error in rl.agent.AbstractAgent/train (line 54)
TrainingStatistics = run(trainMgr);
Error in KleinesModell (line 90)
    trainingStats = train(agent,env,trainingOptions);
Caused by:
    Error using rl.env.SimulinkEnvWithAgent>localHandleSimoutErrors (line 689)
    You cannot set the read-only property 'timestep' of mlep.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Rezky Nanda 2022-4-21

Hi,

I'm currently having the same problem. Have you found the solution to the problem yet?

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Emmanouil Tzorakoleftherakis 2020-11-10

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/624848-timestep-problems-using-reinforcement-learning-with-energyplus#answer_540605

Hello,

I am not familiar with EnergyPlus so I am not sure about the error you are getting (although it seems like you are trying to change the 'timestep' property?), but if you want the agent to provide actions every hour, you just need to set the Ts/sample time agent option to this value.