Homing through Reinforcement Learning
Abstract
Homing and navigation are fundamental behaviors in biological systems that enable agents to reliably reach a target under uncertainty. We present a Reinforcement Learning (RL) framework to model adaptive homing in continuous two-dimensional domain. In this framework, the agent's state is given by its angular deviation from home, actions correspond to alignment or stochastic reorientation, and learning is driven by a radial-distance-based cost that penalizes motion away from the target. For a single self-propelled agent moving with constant speed, we find that the mean homing time exhibits a non-monotonic dependence on the rotational diffusion strength , with an optimal noise level , revealing a subtle interplay between exploration and goal-directed correction. Extending to two agents with soft repulsion, one agent consistently reaches home faster than the other, while in multi-agents system, repulsion ensures separation and the fastest agent becomes progressively faster as group size increases. Finally comparing the mean homing time of an Active Brownian Particle (ABP) and RL agent over an identical range of , we find that RL trajectories are shorter, less noisy, and consistently faster. Our results show that cost-driven learning, stochastic reorientation, and inter-agent interactions enable efficient adaptive navigation, linking individual and collective homing. This reinforcement learning framework captures key biological features such as feedback-based route learning, randomness to escape unfavorable orientations, and mutual coordination.
Cite
@article{arxiv.2602.08566,
title = {Homing through Reinforcement Learning},
author = {Riya Singh and Pratikshya Jena and Anish Kumar and Shradha Mishra},
journal= {arXiv preprint arXiv:2602.08566},
year = {2026}
}