How to set multiple stopping or saving criteria for RL agent?

Hello, I wondered if it is possible to set multiple stopping or saving criteria for RL agent? E.g. Save the agent for average episode reward after 100 episodes.

Thanks in advance.

Answer 1

[Emmanouil Tzorakoleftherakis]

This is currently not possible but keep an eye out on future releases - the development team has been working on this functionality

Answer 2

[Lance]

From what I understand, the only other work around would be to write another training command. You would have to predfine this for every "checkpoint" ie. 10,20,30 episodes. The training-progress graph will continue to be actively updated. (Note I am using R2022a)

% Define all agents, observations, actions, environment, etc....
maxepisodes=500;
trainingOpts=rlMultiAgentTrainingOptions;
trainingOpts.SaveAgentCriteria="EpisodeCount";
trainingOpts.SaveAgentValue=maxepisodes
trainingStats=train([agent1,agent2],environment,trainingOpts); % Will train to max episodes and save agent

% Edit Trainingoptions to increase maxepisodes and save agent value

trainingStats(1,1).TrainingOptions.MaxEpisodes=1000;
trainingStats(1,1).TrainingOptions.SaveAgentValue=[1000,1000];
trainnigStats(1,1).TrainingOptions.StopTrainingValue=[1000,1000];
trainingStats(1,2).TrainingOptions.MaxEpisodes=1000;
trainingStats(1,2).TrainingOptions.SaveAgentValue=[1000,1000];
trainnigStats(1,2).TrainingOptions.StopTrainingValue=[1000,1000];

% Resume training -- Will train to 1000 episodes and save agent again
trainingStats2=train([agent1,agent2],environment,trainingStats) %Note you use trainingStats here not trainingOpts

Let me know if this helps!

[Yihao Wan]

Sure, thanks a lot, Lance. I will try this first.