mlsanityData to 14 Oct 2026

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

arXiv 2605.18881 ↗First posted 16 May 2026cs.LG physics.flu-dyncited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

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.

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.

Builds on

11 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Q-learning with temporal memory to navigate turbulence26 Apr

Other references · 10

  1. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  2. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  3. 2017QMDP-Net: Deep Learning for Planning under Partial Observabilitycited by 51
  4. 2021Partially Observable Markov Decision Processes (POMDPs) and Roboticscited by 49
  5. 2021Learning Efficient Navigation in Vortical Flow Fieldscited by 26
  6. 2019Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learningcited by 21
  7. 2023Deep reinforcement learning for the olfactory search POMDP: a quantitative benchmarkcited by 6
  8. 2022Optimal policies for Bayesian olfactory search in turbulent flowscited by 4
  9. 2021Finite-Horizon, Energy-Optimal Trajectories in Unsteady Flowscited by 3
  10. 2017Reinforcement Learning via Recurrent Convolutional Neural Networkscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Clock-state olfactory search in turbulent flows using Q-learning: The geometry of plume recovery
  2. 2026Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning
  3. 2026Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation
  4. 2024A transformer-based deep reinforcement learning approach to spatial navigation in a partially observable Morris Water Maze
  5. 2025From Pheromones to Policies: Reinforcement Learning for Engineered Biological Swarms
  6. 2025GRL-SNAM: Geometric Reinforcement Learning with Path Differential Hamiltonians for Simultaneous Navigation and Mapping in Unknown Environments
  7. 2025A critical assessment of reinforcement learning methods for microswimmer navigation in complex flows
  8. 2025Privileged observations enable rapid and reliable policy discovery directly in the physical world