# Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring

arXiv: https://arxiv.org/abs/2604.12645 · HTML: https://mlsanity.com/paper/2604.12645/

## Key facts

- Cited by 1 papers in the map (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 17 of its 45 references that are in the map.
- First posted on arXiv 14 Apr 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, 17 of 17)

- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Multi-Task Reinforcement Learning with Context-based Representations](https://mlsanity.com/paper/2102.06177/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [A Survey of Exploration Methods in Reinforcement Learning](https://mlsanity.com/paper/2109.00157/) (2021)
- [Markov Decision Processes with Continuous Side Information](https://mlsanity.com/paper/1711.05726/) (2017)
- [Contextualize Me -- The Case for Context in Reinforcement Learning](https://mlsanity.com/paper/2202.04500/) (2022)
- [Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study](https://mlsanity.com/paper/2108.02665/) (2021)
- [A Framework for On-line Learning of Underwater Vehicles Dynamic Models](https://mlsanity.com/paper/1903.05355/) (2019)
- [Learning of Multi-Context Models for Autonomous Underwater Vehicles](https://mlsanity.com/paper/1809.06179/) (2018)
- [A Preview of HoloOcean 2.0](https://mlsanity.com/paper/2510.06160/) (2025)
- [Deep Adversarial Reinforcement Learning for Object Disentangling](https://mlsanity.com/paper/2003.03779/) (2020)
- [Robot Goes Fishing: Rapid, High-Resolution Biological Hotspot Mapping in Coral Reefs with Vision-Guided Autonomous Underwater Vehicles](https://mlsanity.com/paper/2305.02330/) (2023)

## Built on by (most cited first, 1 of 1)

- [Task-specific Subnetwork Discovery in Reinforcement Learning for Autonomous Underwater Navigation](https://mlsanity.com/paper/2604.21640/) (2026)

## Abstract (arXiv)

Although autonomous underwater vehicles promise the capability of marine ecosystem monitoring, their deployment is fundamentally limited by the difficulty of controlling vehicles under highly uncertain and non-stationary underwater dynamics. To address these challenges, we employ a data-driven reinforcement learning approach to compensate for unknown dynamics and task variations. Traditional single-task reinforcement learning has a tendency to overfit the training environment, thus, limit the long-term usefulness of the learnt policy. Hence, we propose to use a contextual multi-task reinforcement learning paradigm instead, allowing us to learn controllers that can be reused for various tasks, e.g., detecting oysters in one reef and detecting corals in another. We evaluate whether contextual multi-task reinforcement learning can efficiently learn robust and generalisable control policies for autonomous underwater reef monitoring. We train a single context-dependent policy that is able to solve multiple related monitoring tasks in a simulated reef environment in HoloOcean. In our experiments, we empirically evaluate the contextual policies regarding sample-efficiency, zero-shot generalisation to unseen tasks, and robustness to varying water currents. By utilising multi-task reinforcement learning, we aim to improve the training effectiveness, as well as the reusability of learnt policies to take a step towards more sustainable procedures in autonomous reef monitoring.