Could reinforcement learning work in the following context : Given that the initial state space is very large (10^6) and the actions would only effect a subspace of the state could we randomly select a sample(the subspace we want to adjust) from the state? And thus given the observation(sample) take an action for this sample ? And afterwards update the state in a global according to the actions for that sample. And then in the next step feed it a new random sample from this new state?


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.