TABLE 6.

Characteristics of reinforcement learning based source seeking and estimation.

Characteristic	Description
Objective	Locate the source of phenomenon
State Representation	Environmental features, source model grid cells
Action Space	Movement actions, sensing actions
Reward Function	Rewards for locating source
Observation	Intensity/Concentration values of environmental target
Challenges	Noisy and sparse information, dynamic sources, initial search phase
Citations	Duisterhof et al. (2021); Li et al. (2023); Viseras and Garcia. (2019)