[ExI] Deepmind Gato - Another step towards AGI

BillK pharos at gmail.com
Fri May 13 10:33:38 UTC 2022


Published May 12, 2022
Quote:
Inspired by progress in large-scale language modelling, we apply a
similar approach towards building a single generalist agent beyond the
realm of text outputs. The agent, which we refer to as Gato, works as
a multi-modal, multi-task, multi-embodiment generalist policy. The
same network with the same weights can play Atari, caption images,
chat, stack blocks with a real robot arm and much more, deciding based
on its context whether to output text, joint torques, button presses,
or other tokens.

<https://www.deepmind.com/publications/a-generalist-agent>
-----------


Combining more tasks into a single AI is progress towards a
generalised AI that can handle multiple environments and many tasks.
The next step is AI self-teaching when it encounters new tasks and environments.

BillK


More information about the extropy-chat mailing list