Tag: RL
-
Generalization in ML: the indoor training effect
Jan 29, 2025 Is it better to train under noisy conditions to learn to generalize? New work by Serena Bono and Spandan Madan shed light on the mechanisms underlying generalization in reinforcement learning agents. This work led to discovering the indoor training effect whereby agents can improve their generalization performance under certain circumstances when trained… Read more
-
Harvard. The interneuron, July 2024
july 2, 2024 AI agents help worms find food by integrating with their nervous system Harvard’s The Interneuron highlights the work of Chenguang Li describing a hybrid between biological and artificial neural networks. Li and colleagues showed how to enhance behavior in the C. elegans worm by elegantly combining optogenetics, computer vision, and reinforcement learning.… Read more