Reward is enough

Jul 4, 2021

“Reward is enough”

This is an interesting paper saying that “reward” and reward maximization is a single principle that can lead to all forms of intelligent behavior. They are basically saying reinforcement learning is enough.

My question : why maximize? What about multilple conflicting rewards?

From the abstract: “In this article we hypothesise that intelligence, and its associated abilities, can be understood as subserving the maximisation of reward. Accordingly, reward is enough to drive behaviour that exhibits abilities studied in natural and artificial intelligence, including knowledge, learning, perception, social intelligence, language, generalisation and imitation.”

SCIENCEDIRECT.COM

Reward is enough

In this article we hypothesise that intelligence, and its associated abilities, can be understood as subserving the maximisation of reward. Accordingl…

https://www.sciencedirect.com/science/article/pii/S0004370221000862

← Back to all articles         Quick Navigation:    Next:[ j ] – Prev:[ k ] – List:[ l ]