Autotaxis of a Run-and-Tumble Agent via Reinforcement Learning
Abstract
We study the run-tumble motion of a single autochemotactic agent that secretes and senses chemical cues using a reinforcement learning (RL) framework. In a chemical environment that changes dynamically via secretion, diffusion, and degradation of attractant chemicals, we study the effectiveness of RL for a successful navigation strategy. We show that RL enhances chemotactic performance. Starting from a random initial position, the probability of finding the agent in the favorable region (near the attractant peak) increases faster with time and reaches a higher value in the long time limit when RL is used, compared to the case when the agent performs usual run-tumble chemotaxis without using RL. We also characterize the chemotactic performance of the agent by varying different parameters like rates of secretion, degradation, and diffusion. Importantly, we observe a non-monotonic dependence of the chemotactic performance on the learning and exploration rates, indicating the existence of an optimal RL strategy for the most efficient navigation. We explain these observations as a result of the interplay between the pre-existing attractant environment and the agent-generated attractant profile.
Versions
Related
- Multi-agent meta-reinforcement learning based on contrastive predictive coding—For rapid adaptive traffic control after emergencies
- Deterministic dynamics of distributional multi-agent reinforcement learning
- Reliability-based arbitration reveals heterogeneous model-based and model-free reinforcement learning strategies linked to compulsivity and impulsivity
- Reinforcement learning as a foundation for psychodynamics
- Increased monetary incentives enhance goal-directed reinforcement learning but fail to suppress automatic learning processes
BibTeX
@misc{pramanik2026autotaxis,
title = {{Autotaxis of a Run-and-Tumble Agent via Reinforcement Learning}},
author = {Ramesh Pramanik and Shradha Mishra and Sakuntala Chatterjee},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.07531},
eprint = {2611.07531},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.07531},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Autotaxis of a Run-and-Tumble Agent via Reinforcement Learning
AU - Ramesh Pramanik
AU - Shradha Mishra
AU - Sakuntala Chatterjee
PY - 2026
DA - 2026/11/05
PB - arXiv
DO - 10.48550/arxiv.2611.07531
UR - https://arxiv.org/abs/2611.07531
AB - We study the run-tumble motion of a single autochemotactic agent that secretes and senses chemical cues using a reinforcement learning (RL) framework. In a chemical environment that changes dynamically via secretion, diffusion, and degradation of attractant chemicals, we study the effectiveness of RL for a successful navigation strategy. We show that RL enhances chemotactic performance. Starting from a random initial position, the probability of finding the agent in the favorable region (near the attractant peak) increases faster with time and reaches a higher value in the long time limit when RL is used, compared to the case when the agent performs usual run-tumble chemotaxis without using RL. We also characterize the chemotactic performance of the agent by varying different parameters like rates of secretion, degradation, and diffusion. Importantly, we observe a non-monotonic dependence of the chemotactic performance on the learning and exploration rates, indicating the existence of an optimal RL strategy for the most efficient navigation. We explain these observations as a result of the interplay between the pre-existing attractant environment and the agent-generated attractant profile.
ER -