Reinforcement Learning experience buffer length and parallelisation toolbox
4 views (last 30 days)
Show older comments
Tech Logg Ding
on 2 Dec 2020
Edited: Emmanouil Tzorakoleftherakis
on 3 Dec 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 Comments
Accepted Answer
Emmanouil Tzorakoleftherakis
on 3 Dec 2020
Edited: Emmanouil Tzorakoleftherakis
on 3 Dec 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 Comments
More Answers (0)
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!