Get the latest tech news
Supporting Task Switching with Reinforcement Learning
Multitasking can be categorized among various dimensions, such as the time spent on a task [67 ], task complexity, relation to the primary task, continuous vs. discrete tasks, and of course, the tasks’ demand on perceptual, cognitive, and physical resources [13 ].
Additionally, we investigated if the task switching behavior of our best-performing AMS agent (the one trained using the cognitive model) differs from the participants’ self-chosen interruption strategy ( no supervisor condition) using Wilcoxon signed rank tests, see Figure 6. Saleema Amershi, Dan Weld, Mihaela Vorvoreanu, Adam Fourney, Besmira Nushi, Penny Collisson, Jina Suh, Shamsi Iqbal, Paul N. Bennett, Kori Inkpen, Jaime Teevan, Ruth Kikin-Gil, and Eric Horvitz. Other Metrics Lingler A Talypova D Wintersberger P(2024) AITentive: A Toolkit to Develop RL-based Attention Management Systems Adjunct Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology 10.1145/3672539.3686314(1-3) Online publication date: 13-Oct-2024
Or read this on Hacker News