By Exploring Virtual Worlds, AI Learns in New Ways

#105 · ✸ 63 · 💬 41 · one year ago · www.quantamagazine.org · pseudolus · 📷
One easy way to measure embodied AI's progress is by comparing embodied agents' performance to algorithms trained on the simpler, static image tasks. Researchers note these comparisons aren't perfect, but early results do suggest that embodied AI agents learn differently - and at times better - than their forebears. In two separate papers, one led by Clay and the other by Grace Lindsay, an incoming professor at New York University, researchers found that the neural networks in embodied agents had fewer neurons active in response to visual information, meaning that each individual neuron was more selective about what it would respond to. While comparing embodied neural networks to nonembodied ones is one measure of progress, researchers aren't really interested in improving embodied agents' performance on current tasks; that line of work will continue separately, using traditionally trained AI. The true goal is to learn more complicated, humanlike tasks, and that's where researchers have been most excited to see signs of impressive progress, particularly in navigation tasks. Navigation still represents one of the simplest tasks in embodied AI, since the agents move through the environment without manipulating anything in it. Embodied AI agents are far from mastering any tasks with objects. Robots are, inherently, embodied intelligence agents.
By Exploring Virtual Worlds, AI Learns in New Ways



Send Feedback | WebAssembly Version (beta)