Re:Why machine learning struggles with causality
by dumbfoundded on Friday April 02, 2021 @12:12PM
(#26672735)
An interesting related idea is inverse reinforcement learning. We watch how other people interact with a system to estimate a reward function and then we later test it out ourselves. Either directly with an environment or inside our own mental model of the environment. Simply "observing the world" can give us data about how to learn in an environment we've never interacted with before; only by watching others interact with it.
[ Parent
| on HN ]
Re:Why machine learning struggles with causality
by still_grokking on Friday April 02, 2021 @05:05PM
(#26675992)
That's true. But the key seems to remain the "interaction with the world".
Re:Why machine learning struggles with causality
by dumbfoundded on Friday April 02, 2021 @05:51PM
(#26676350)
Maybe it's semantics but interacting with a simulation of the world is actually more important. In a pure sense, this doesn't require any actual real world interaction. This concept is usually referred to offline and off-policy reinforcement learning.
If you're saying that interaction in any sense is important, I'd very much agree that unsupervised learning and supervised learning aren't equipped to handle reinforcement learning problems. Correct framing of a problem is necessary to achieve a desired property like causality.