Telegram Group & Telegram Channel
This media is not supported in your browser
VIEW IN TELEGRAM
Еще интересный подход по созданию агентов (на базе Vision language модели) с RLем которые могут пользоваться Android телефоном через GUI

Вначале трейнят offline RL на данных, потом offline-to-online где агент уже сам доучивается в среде. Создали распараллеленный симулятор который одновременно может запускать 64 эмулятора андроида.

Тестировались на датасете Android-in-the-Wild (AitW). VLMка на 1.3B параметров.

* success rate подняли до 67.2%

у другого RL агента который учился через Behavior cloning был - 57.8%

GPT-4V - 8.3%
Gemini 1.5 Pro - 17.7%
17B CogAgent - 38.5%

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
https://arxiv.org/abs/2406.11896

https://digirl-agent.github.io/
https://github.com/DigiRL-agent/digirl
🔥7👍2



group-telegram.com/AGI_and_RL/800
Create:
Last Update:

Еще интересный подход по созданию агентов (на базе Vision language модели) с RLем которые могут пользоваться Android телефоном через GUI

Вначале трейнят offline RL на данных, потом offline-to-online где агент уже сам доучивается в среде. Создали распараллеленный симулятор который одновременно может запускать 64 эмулятора андроида.

Тестировались на датасете Android-in-the-Wild (AitW). VLMка на 1.3B параметров.

* success rate подняли до 67.2%

у другого RL агента который учился через Behavior cloning был - 57.8%

GPT-4V - 8.3%
Gemini 1.5 Pro - 17.7%
17B CogAgent - 38.5%

DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
https://arxiv.org/abs/2406.11896

https://digirl-agent.github.io/
https://github.com/DigiRL-agent/digirl

BY Агенты ИИ | AGI_and_RL


Share with your friend now:
group-telegram.com/AGI_and_RL/800

View MORE
Open in Telegram


Telegram | DID YOU KNOW?

Date: |

Pavel Durov, a billionaire who embraces an all-black wardrobe and is often compared to the character Neo from "the Matrix," funds Telegram through his personal wealth and debt financing. And despite being one of the world's most popular tech companies, Telegram reportedly has only about 30 employees who defer to Durov for most major decisions about the platform. Telegram boasts 500 million users, who share information individually and in groups in relative security. But Telegram's use as a one-way broadcast channel — which followers can join but not reply to — means content from inauthentic accounts can easily reach large, captive and eager audiences. Two days after Russia invaded Ukraine, an account on the Telegram messaging platform posing as President Volodymyr Zelenskiy urged his armed forces to surrender. "And that set off kind of a battle royale for control of the platform that Durov eventually lost," said Nathalie Maréchal of the Washington advocacy group Ranking Digital Rights. The gold standard of encryption, known as end-to-end encryption, where only the sender and person who receives the message are able to see it, is available on Telegram only when the Secret Chat function is enabled. Voice and video calls are also completely encrypted.
from ye


Telegram Агенты ИИ | AGI_and_RL
FROM American