Iterative trial-and-error is not the same as closed-loop feedback. In the former, the error signal is only usable for the next trial, not to recover the current trial. Trial and error modulates discontinuous structural evolution rather than continuous behavioral progression.
-
-
There’s got to be a way to state this in a rigorous way. I think a trial-and-error loop is one that does not converge to a continuous transfer function in the limit of making the iteration interval smaller because there’s a process step that’s not bounded as function of step size
Show this thread -
Ie closed-loop assumes strongly bounded rationality in the feedback transfer function. You can do the e(t) —> u(t) computation in delta_t, as it goes to zero. Because e(t) gets smaller because stability.
Show this thread -
Human-in-the-loop is nearly the same as NP-hard problem solver in the loop, where the human can choose a particular good-enough heuristic solution in the time available. Ie, an agent that can change the problem when it can’t stretch the time. Ie a judging/valuing agent.
Show this thread -
Sorry, thinking out loud down a pseudo-mathematical bunnytrail. This is control theory geekery of as yet unclear relevance to practical things.
Show this thread
End of conversation
New conversation -
-
-
This is getting blurred these days due to Reinforcement Learning: episodic RL falls into what you call trial and error. Hierarchical RL would aim to tune both loops simultaneously.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.