"So imagine that you have some kind of probability distribution over the worlds that the robot could actually end up operating in. I want to find a program that's going to behave well, let's say get a lot of reward in expectation on average over all the environments that it could possibly find itself in. So that's, I would say, kind of a reasonable formal objective for a robot. And one thing that's good about this as an objective is that we don't have to argue about it, right? It doesn't say whether there should be learning in there or what kind of learning or should it be a genetic algorithm or should it have planning. In some sense, you could say, "I just want to make the program that's going to be the best that can be on average over these environments.""
Quote Details
Added by wikiquote-import-bot
Unverified quote
0 likes
Computer scientists from the United StatesWomen academics from the United StatesStanford University alumniWomen scientists from the United StatesMassachusetts Institute of Technology faculty
Original Language: English
Available Languages (1)
Sources
Imported from EN Wikiquote
https://en.wikiquote.org/wiki/Leslie_P._Kaelbling
Revision History
No revisions have been submitted for this quote.
Categories
Leslie P. Kaelbling
Leslie Pack Kaelbling is an American roboticist and the Panasonic Professor of Computer Science and Engineering at the Massachusetts Institute of Technology. She is widely recognized for adapting partially observable Markov decision processes from operations research for application in artificial intelligence and robotics. Kaelbling received the IJCAI Computers and Thought Award in 1997 for applying reinforcement learning to embedded control systems and developing programming tools for robot nav
33 quotes on TrueQuotesView all quotes by Leslie P. Kaelbling →
Related Quotes
"Fundamentally, the way we think about it is that we decompose the computation that's in the robot's head now into two…"
"So the dimensionality of the space is kind of unthinkably high. It's also not exactly clear what constitutes an objec…"
"And so any approach that works effectively in a domain like this is going to have to handle very large spaces, very l…"
"The reason I want to start by backing all the way up to this like very basic control theory picture is that right now…"
"So one way to think about the whole problem set up then is that I, as the robotics engineer, have to do for my robots…"
"So I imagine that there's some distribution over possible environments that the robot could find itself in when it ac…"
"And so what we want to do is think about first of all, what's the best-- what would be the best pi to put inside the …"
"So there are a bunch of ways you can think about the problem. I mean, one would be to say, "Oh, I'm really lazy. I do…"
"Another strategy-- and this is like the classic engineering strategy-- is that, no, I'm like a serious engineer. And …"
"But the problem is now I've written down an objective function. I've said, "Oh, if you could tell me a distribution o…"