0
$\begingroup$

I want to develop an AI for continuous space. I reached to DDPG algorithm that takes actions deterministically.

If DDPG takes actions deterministically, should the environment also be deterministic? I want non-deterministic, continuous real-world environments. Is DDPG the algorithm I am looking for? Is there any other algorithm for my need?

|improve this question
$\endgroup$
2
$\begingroup$

I am not an expert in this area. But I believe that the word "Deterministic" is for "Policy" in the "Deterministic Policy" Gradient. It does not mean deterministic environment.

Stochastic policy: Probabilistic(random) action choice for a given state.
Deterministic policy: one action is chosen for a given state.

Deterministic Policy Gradient algorithm still can handle a stochastic (and continuous, of cause) environment, but the policy will be deterministic.

Reference

"in DDPG, the Actor directly maps states to actions (the output of the network directly the output) instead of outputting the probability distribution across a discrete action space" -towards Data Science

Deterministic Policy Gradient Algorithms by Silver et al. PDF

|improve this answer
$\endgroup$
  • $\begingroup$ thank you. I also read this from the source but i cant get it. Recently i read a nice tutorial that has implementation and it accurate. On that tutorial there is a line says: "Deterministic policies are used in deterministic environments. These are environments where the actions taken determine the outcome. There is no uncertainty" and this makes me confused! I don't know what I have to do. I read a lot but cant find anything that verify this. i read that here: freecodecamp.org/news/… $\endgroup$ – Fcoder Jul 5 '19 at 17:49

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.