Searching for a source without gradients: how good is infotaxis and how to beat it

TL;DR

This paper evaluates the performance of infotaxis in source search tasks across multiple dimensions, introduces strategies to surpass it, and demonstrates deep reinforcement learning's ability to find near-optimal solutions without prior knowledge.

Contribution

The study provides an extensive review of infotaxis, compares its performance across dimensions, and introduces AI-inspired methods, including deep reinforcement learning, to improve search strategies.

Findings

Infotaxis is reliable, efficient, and safe but suboptimal.

Deep reinforcement learning can discover near-optimal strategies without prior knowledge.

The potential for improvement of infotaxis decreases as the search space dimensionality increases.

Abstract

Infotaxis is a popular search algorithm designed to track a source of odor in a turbulent environment using information provided by odor detections. To exemplify its capabilities, the source-tracking task was framed as a partially observable Markov decision process consisting in finding, as fast as possible, a stationary target hidden in a 2D grid using stochastic partial observations of the target location. Here we provide an extended review of infotaxis, together with a toolkit for devising better strategies. We first characterize the performance of infotaxis in domains from 1D to 4D. Our results show that, while being suboptimal, infotaxis is reliable (the probability of not reaching the source approaches zero), efficient (the mean search time scales as expected for the optimal strategy), and safe (the tail of the distribution of search times decays faster than any power law, though subexponentially). We then present three possible ways of beating infotaxis, all inspired by methods used in artificial intelligence: tree search, heuristic approximation of the value function, and deep reinforcement learning. The latter is able to find, without any prior human knowledge, the (near) optimal strategy. Altogether, our results provide evidence that the margin of improvement of infotaxis toward the optimal strategy gets smaller as the dimensionality increases.