Preparing data for training an autoencoder

Home / Research / Dissertation / Preparing data for training an autoencoder

I’m training a relational autoencoder using data from two Markov Decision processes tasks: the Mountain Car task and the Inverted Pendulum (or Cart-Pole) task.  To do this, I need to map the sample data to nodes in the input layer (and output layer) in the relational autoencoder.  I see this as follows:

Mountain Car

  • Position – real/real
  • Velocity – real/real
  • forward action – boolean {0,1} / sigmoidal
  • backward action – boolean {0,1} / sigmoidal
  • coast action – boolean {0,1} / sigmoidal

Cart Pole

  •  θ – real/real
  • ω – real/real
  • x – real/real
  • v – real/real
  • force action – real/real

My chair and I discussed the actions as being discrete, but most implementations have a variable force as an action.  So, we’re going to address it as such.  This gives a different action space than the other task which is towards the objective of cross-modal learning.



Leave a Reply

Your email address will not be published. Required fields are marked *

%d bloggers like this: