Reinforcement Learning experience buffer length and parallelisation toolbox
3 Ansichten (letzte 30 Tage)
Ältere Kommentare anzeigen
Tech Logg Ding
am 2 Dez. 2020
Bearbeitet: Emmanouil Tzorakoleftherakis
am 3 Dez. 2020
When parallelisation is used when training a DDPG agent with the following settings:
trainOpts.UseParallel = true;
trainOpts.ParallelizationOptions.Mode = 'async';
trainOpts.ParallelizationOptions.StepsUntilDataIsSent = -1;
trainOpts.ParallelizationOptions.DataToSendFromWorkers = 'Experiences';
Does the the parallel simulations have their own experience buffer? This could take up more memory hence I am hoping that only one experience buffer is stored to update the critic network.
From the documentations, it seems like there will only be one experience buffer as the experiences are sent back to the host.
0 Kommentare
Akzeptierte Antwort
Emmanouil Tzorakoleftherakis
am 3 Dez. 2020
Bearbeitet: Emmanouil Tzorakoleftherakis
am 3 Dez. 2020
Hello,
There is one big experience buffer on the host, the size of which you determine as usual in your agent options. Each worker has a much smaller buffer to collect experiences until you reach "StepsUntilDataIsSent".
0 Kommentare
Weitere Antworten (0)
Siehe auch
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!