I am using a policy gradient algorithm (actor-critic) for wireless networks. The policy gradient-based algorithm helps because it considers continuous action space.

But how much does a policy gradient-based algorithm contribute to the complexity of the involved neural networks, compared to discrete action space algorithms (like Q-learning)? Moreover, in terms of computation, how do policy gradient algorithms (for continuous action spaces) compare to discrete action space algorithms?

  • $\begingroup$ Hi and welcome to this community! Can you please clarify what you mean by "system complexity"? $\endgroup$
    – nbro
    Nov 7 '19 at 16:10
  • $\begingroup$ What do you mean by "I am using a policy gradient algorithm for wireless networks". Can you clarify exactly how you're using the policy gradient algorithms in the context of wireless networks? $\endgroup$
    – nbro
    Nov 8 '19 at 14:31

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.