I have a question with regard to Q learning. I am a beginner in Q learning. Every example that I saw is related to the environment that the goal is assigned to a place. (like cliff walk that we know where the agent should go). But I have a problem that I don't know where is my goal. For example, I have an output (take it as y= a *input+b, I should find a and b, I have one actual output of y also, and I know the range of a and b, for example, 1

  • $\begingroup$ for example, 1<a<3 and 4<b<6, so I have space and I want to find the exact a and b. for example exact a and b should be (1.5, 5). Could anyone help me to define the reward and also how should I move between the spaces? Or could you have listed any paper and example like this for me? thank you so much $\endgroup$ – Hasan Mar 2 at 17:50

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.