I'm running A3C (Asynchronous Actor-Critic Agents) to learn a game where an agent needs to catch 3 rewards. The input of my network, among other things, is the relative position of the 3 rewards against the agent.

However, as the agent catches these rewards, my network can't just decrease its input size. What are ways of handling this?

My current solutions have been:

  • set remaining features to zero - have tried, bad results

  • just show the closest reward - loss of information, might not be optimal

  • repeat existing reward positions to remaining features - we are giving more emphasis to some rewards (the ones that are repeated) over others

  • $\begingroup$ Have you tried adding an additional, binary feature indicating for each reward if it has already been caught? $\endgroup$
    – user12889
    Oct 27 '17 at 2:45
  • $\begingroup$ @user12889 Great idea, actually, I hadn't thought of that $\endgroup$
    – BlueMoon93
    Oct 27 '17 at 8:08

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.