Remix.run Logo
whatever1 3 days ago

This is very typical in reinforcement learning. You just expand the state to include some more time periods. It definitely raises some academic eyebrows (since it’s not technically memory less), but hey if it works, it works

jvanderbot 3 days ago | parent [-]

It is memoryless just in a different state space.

whatever1 3 days ago | parent [-]

In the state space that includes all of the time periods, with infinitesimal granularity since the birth of the universe.

jvanderbot 3 days ago | parent [-]

Welcome to a well formulated POMDP.