Reinforcement Learning Memory Error

When I turn on the SaveExperienceBufferWithAgent, I get the following error:

Warning: Unable to save the agent to the directory "savedAgents". Increase the
disk space or check SaveAgentCriteriaValue in training options. 
> In rl.train/TrainingManager/saveAgentToDisk (line 653)
In rl.train/TrainingManager/updateDisplaysFromTrainingInfo (line 717)
In rl.train/TrainingManager/update (line 147)
In rl.train.TrainingManager>@(info)update(this,info) (line 437)
In rl.train/Trainer/notifyEpisodeFinishedAndCheckStopTrain (line 56)
In rl.train.SeriesTrainer>iUpdateEpisodeFinished (line 31)
In rl.train.SeriesTrainer>@(src,ed)iUpdateEpisodeFinished(this,ed) (line 17)
In rl.env/AbstractEnv/notifyEpisodeFinished (line 324)
In rl.env.SimulinkEnvWithAgent.executeSimsWrapper/nestedSimFinishedBC (line 222)
In rl.env.SimulinkEnvWithAgent>@(src,ed)nestedSimFinishedBC(ed) (line 232)
In Simulink/SimulationManager/handleSimulationOutputAvailable
In Simulink.SimulationManager>@(varargin)obj.handleSimulationOutputAvailable(varargin{:})
In MultiSim.internal/SimulationRunnerSerial/executeImplSingle
In MultiSim.internal/SimulationRunnerSerial/executeImpl
In Simulink/SimulationManager/executeSims
In Simulink/SimulationManagerEngine/executeSims
In rl.env/SimulinkEnvWithAgent/executeSimsWrapper (line 244)
In rl.env/SimulinkEnvWithAgent/simWrapper (line 267)
In rl.env/SimulinkEnvWithAgent/simWithPolicyImpl (line 424)
In rl.env/AbstractEnv/simWithPolicy (line 82)
In rl.task/SeriesTrainTask/runImpl (line 33)
In rl.task/Task/run (line 21)
In rl.task/TaskSpec/internal_run (line 166)
In rl.task/TaskSpec/runDirect (line 170)
In rl.task/TaskSpec/runScalarTask (line 194)
In rl.task/TaskSpec/run (line 69)
In rl.train/SeriesTrainer/run (line 24)
In rl.train/TrainingManager/train (line 421)
In rl.train/TrainingManager/run (line 211)
In rl.agent.AbstractAgent/train (line 78)

The disk that I am running it on still has 100 GB of space. What is causing this issue?

[Stephan]

Are there any saved agents or is the directory empty?

[Tech Logg Ding]

The saved agents folder is shown in the picture below. The training ran for ~ 2 days and MATLAB and my pc crashed (possibly due to insufficient RAM ~ I have 32 GB now). It was starting to converge to an optimal but unfortunately the results couldn't be saved. The first agent that met the criteria was saved but the rest of them are small files that cannot be loaded.

When I try to load them, I get the following error:

>> load('D:\Tuning VCRS Model\savedAgents\Agent1336.mat')
Error using load
Cannot read file D:\Tuning VCRS Model\savedAgents\Agent1336.mat.

[Emmanouil Tzorakoleftherakis]

Can you create a technical support case? This is strange.

Aside from that, is there a reason you are saving the experience buffer in all these agents? Typically, saving the experience buffer is helpful if you want to begin training from that specific point in time. Otherwise you don't really need it for inference

[Tech Logg Ding]

Okay, I'll create a technical support case.

I created the experience buffer initially to have a 'save point' if the training crashes. However, i have turned it off and I still have the same issue.

[Hasan Khanzada]

Your problem is solved ? because i am having the same issue as you were.