Q-Learning to navigate turbulence without a map

arXiv:2404.17495v1 Announce Type: cross
Abstract: We consider the problem of olfactory searches in a turbulent environment. We focus on agents that respond solely to odor stimuli, with no access to spatial perception nor prior information about the odor location. We ask whether navigation strategies to a target can be learned robustly within a sequential decision making framework. We develop a reinforcement learning algorithm using a small set of interpretable olfactory states and train it with realistic turbulent odor cues. By …

abstract access agents arxiv cs.lg environment focus information location map navigation perception physics.bio-ph prior q-learning spatial strategies turbulence type