Users love the chaotic nature of applying reinforcement learning to live websites, where the DOM shifts with every new product manager idea.
Based on 1 visible X reactions from 2 accounts; directional sample.
Ask a question below.
Published answers will appear here.
@ziv_ravid @DhruvBatra_ rl on live websites is unhinged. training on a dom that changes every time a pm has a new idea. i love the chaos.
New episode of the Information Bottleneck with Dhruv Batra (@DhruvBatra_ ), co-founder of Yutori and former head of Embodied AI at Meta FAIR. He spent years training robots to navigate 3D scans, and now he builds web agents, and he says it's the same job, and the browser is just a cheaper place to fail.. Also: RL on live websites, and who pays for the web when agents do the browsing. Link below 👇
fun chat about the similarities between physical agents (robots) and digital agents (computer use / browser use). thanks for having me!
Users love the chaotic nature of applying reinforcement learning to live websites, where the DOM shifts with every new product manager idea.
Based on 1 visible X reactions from 2 accounts; directional sample.
Ask a question below.
Published answers will appear here.