[FRIAM] the good news is, it will be over soon

[glen]

https://smmry.com/https://www.deepmind.com/publications/a-generalist-agent#&SM_LENGTH=2
> The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy.
> 
> Gato is trained on a large number of datasets comprising agent experience in both simulated and real-world environments, in addition to a variety of natural language and image datasets.

GPT-3 Davinci:
> Gato is 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.


On 5/18/22 06:12, Marcus Daniels wrote:
> https://www.deepmind.com/publications/a-generalist-agent <https://www.deepmind.com/publications/a-generalist-agent>

-- 
Mɥǝu ǝlǝdɥɐuʇs ɟᴉƃɥʇ' ʇɥǝ ƃɹɐss snɟɟǝɹs˙