Simple Reinforcement Learning with Tensorflow Part 6: Partial Observability and Deep Recurrent…
Arthur Juliani

On a different note,

#Add the episode to the experience buffer
bufferArray = np.array(episodeBuffer)
episodeBuffer = zip(bufferArray)

In the above block, do you need the pre-processing of episodeBuffer (first 2 lines) before putting into myBuffer?

For me, just myBuffer.add(episodeBuffer) without the first 2 lines seems to work just fine…

Do you have some performance gain if you do the pre-processing ?

Like what you read? Give John Park a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.