Scalar Reward is Not Enough

• Silver et al.[14] posit that scalar reward maximisation is sufficient to underpin all intelligence and provides a suitable basis for artificial general intelligence (AGI). This extended abstract summarises the counter-argument from our JAAMAS paper [19].

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Scalar rewards

Vector rewards

AGI

Reinforcement learning

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)