Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration — mentioned by itissid

Thu, 30 Nov 2023 16:42:45 GMT

Like in Workflow Guided explorations like: https://arxiv.org/pdf/1802.08802.pdf, for example, if you said "Forward the email" the Bot needs to sample from a set of actions which in this case would be DOM elements and the JS API to call to click the right button to forward the email. This would be a harder/interesting to test out. Can it learn to forward an email on firefox desktop browser and then do it on an iphone? It feels like opening a drawer once learn't, the bot has a (world?) model of what all drawers might look like, so it can open different drawers in any world. But this might not…

Paper and discussion history. A mention is not an endorsement.

Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration · HackerPapers discussions

Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration — mentioned by itissid