# Reinforcement learning of optimal active particle navigation

arXiv: https://arxiv.org/abs/2202.00812 · HTML: https://mlsanity.com/paper/2202.00812/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 16 references that are in the map.
- First posted on arXiv 1 Feb 2022.

## Builds on (most cited first, 3 of 3)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Benchmarking Deep Reinforcement Learning for Continuous Control](https://mlsanity.com/paper/1604.06778/) (2016)

## Built on by (most cited first, 6 of 6)

- [Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior](https://mlsanity.com/paper/2307.06175/) (2023)
- [Reinforcement Learning for Active Matter](https://mlsanity.com/paper/2503.23308/) (2025)
- [Training microrobots to swim by a large language model](https://mlsanity.com/paper/2402.00044/) (2024)
- [Learning to swim efficiently in a nonuniform flow field](https://mlsanity.com/paper/2212.11482/) (2022)
- [Dynamic control of self-assembly of quasicrystalline structures through reinforcement learning](https://mlsanity.com/paper/2309.06869/) (2023)
- [Reinforcement Learning Enables Autonomous Microrobot Navigation and Intervention in Simulated Blood Capillaries](https://mlsanity.com/paper/2606.26154/) (2026)

## Abstract (arXiv)

The development of self-propelled particles at the micro- and the nanoscale has sparked a huge potential for future applications in active matter physics, microsurgery, and targeted drug delivery. However, while the latter applications provoke the quest on how to optimally navigate towards a target, such as e.g. a cancer cell, there is still no simple way known to determine the optimal route in sufficiently complex environments. Here we develop a machine learning-based approach that allows us, for the first time, to determine the asymptotically optimal path of a self-propelled agent which can freely steer in complex environments. Our method hinges on policy gradient-based deep reinforcement learning techniques and, crucially, does not require any reward shaping or heuristics. The presented method provides a powerful alternative to current analytical methods to calculate optimal trajectories and opens a route towards a universal path planner for future intelligent active particles.