# Emergence of a Flow-Assisted Casting Strategy for Olfactory Navigation via Memory-Augmented Reinforcement Learning

arXiv: https://arxiv.org/abs/2605.18881 · HTML: https://mlsanity.com/paper/2605.18881/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods.
- Builds on 11 of its 45 references that are in the map.
- First posted on arXiv 16 May 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 11 of 11)

- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [QMDP-Net: Deep Learning for Planning under Partial Observability](https://mlsanity.com/paper/1703.06692/) (2017)
- [Partially Observable Markov Decision Processes (POMDPs) and Robotics](https://mlsanity.com/paper/2107.07599/) (2021)
- [Learning Efficient Navigation in Vortical Flow Fields](https://mlsanity.com/paper/2102.10536/) (2021)
- [Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning](https://mlsanity.com/paper/1907.08591/) (2019)
- [Deep reinforcement learning for the olfactory search POMDP: a quantitative benchmark](https://mlsanity.com/paper/2302.00706/) (2023)
- [Q-learning with temporal memory to navigate turbulence](https://mlsanity.com/paper/2404.17495/) (2024)
- [Optimal policies for Bayesian olfactory search in turbulent flows](https://mlsanity.com/paper/2207.04277/) (2022)
- [Finite-Horizon, Energy-Optimal Trajectories in Unsteady Flows](https://mlsanity.com/paper/2103.10556/) (2021)
- [Reinforcement Learning via Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1701.02392/) (2017)

## Abstract (arXiv)

In dynamic flow fields, various animals exhibit remarkable odor search capabilities despite relying on stochastic detections. Interestingly, there exists an optimal time window for integrating these detections that maximizes search efficiency. To understand the underlying mechanism, we investigate the navigation performance of Reinforcement Learning (RL) agents in unsteady flows under varying memory lengths and flow conditions. Without any predefined models, the agents develop a flow-assisted casting strategy and adaptively adjust both the geometry of their search trajectories and the concentration threshold for initiating casting to maximize the success rate. The agent's average speed toward the odor source exhibits a non-monotonic dependence on memory length, which can be explained by the "sector-search" model.