Reinforcement Learning experience buffer length and parallelisation toolbox

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.

Answer 1

[Emmanouil Tzorakoleftherakis]

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".