Encouraging reactivity to create robust machines
Abbreviated Journal Title
EVOLUTIONARY ROBOTICS; NEURAL-NETWORKS; REALITY GAP; CONTROLLER; SIMULATION; Computer Science, Artificial Intelligence; Psychology, Experimental; Social Sciences, Interdisciplinary
The robustness of animal behavior is unmatched by current machines, which often falter when exposed to unforeseen conditions. While animals are notably reactive to changes in their environment, machines often follow finely tuned yet inflexible plans. Thus, instead of the traditional approach of training such machines over many different unpredictable scenarios in detailed simulations (which is the most intuitive approach to inducing robustness), this work proposes to train machines to be reactive to their environment. The idea is that robustness may result not from detailed internal models or finely tuned control policies but from cautious exploratory behavior. Supporting this hypothesis, robots trained to navigate mazes with a reactive disposition prove more robust than those trained over many trials yet not rewarded for reactive behavior in both simulated tests and when embodied in real robots. The conclusion is that robustness may neither require an accurate model nor finely calibrated behavior.
"Encouraging reactivity to create robust machines" (2013). Faculty Bibliography 2010s. 4286.