# MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics

arXiv: https://arxiv.org/abs/2503.09203 · HTML: https://mlsanity.com/paper/2503.09203/

## Key facts

- Cited by 8 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 14 of its 51 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## 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, 14 of 14)

- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Learning agile and dynamic motor skills for legged robots](https://mlsanity.com/paper/1901.08652/) (2019)
- [Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments](https://mlsanity.com/paper/2301.04195/) (2023)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots](https://mlsanity.com/paper/2410.21229/) (2024)
- [OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control](https://mlsanity.com/paper/2309.12825/) (2023)
- [UNav-Sim: A Visually Realistic Underwater Robotics Simulator and Synthetic Data-generation Framework](https://mlsanity.com/paper/2310.11927/) (2023)
- [DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulator](https://mlsanity.com/paper/2209.02862/) (2022)
- [Stonefish: Supporting Machine Learning Research in Marine Robotics](https://mlsanity.com/paper/2502.11887/) (2025)
- [Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Study](https://mlsanity.com/paper/2108.02665/) (2021)
- [Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehicles](https://mlsanity.com/paper/1909.03204/) (2019)
- [Online Approximate Optimal Station Keeping of a Marine Craft in the Presence of a Current](https://mlsanity.com/paper/1710.10511/) (2017)
- [AAM-SEALS: Developing Aerial-Aquatic Manipulators in SEa, Air, and Land Simulator](https://mlsanity.com/paper/2412.19744/) (2024)

## Built on by (most cited first, 8 of 8)

- [A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI](https://mlsanity.com/paper/2505.01458/) (2025)
- [Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles](https://mlsanity.com/paper/2512.13359/) (2025)
- [OceanGym: A Benchmark Environment for Underwater Embodied Agents](https://mlsanity.com/paper/2509.26536/) (2025)
- [Average-Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learning](https://mlsanity.com/paper/2606.25680/) (2026)
- [Towards Scaling Marine Perception with Synthetic Data](https://mlsanity.com/paper/2609.20680/) (2026)
- [AquaOrbit: Sim-to-Real Reinforcement Learning for Underwater Target Orbiting under Intermittent Visual Feedback](https://mlsanity.com/paper/2609.24054/) (2026)
- [A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Sim](https://mlsanity.com/paper/2610.04949/) (2026)
- [Sim-to-Real RL for ASVs using SysID](https://mlsanity.com/paper/2610.12202/) (2026)

## Abstract (arXiv)

This work presents the MarineGym, a high-performance reinforcement learning (RL) platform specifically designed for underwater robotics. It aims to address the limitations of existing underwater simulation environments in terms of RL compatibility, training efficiency, and standardized benchmarking. MarineGym integrates a proposed GPU-accelerated hydrodynamic plugin based on Isaac Sim, achieving a rollout speed of 250,000 frames per second on a single NVIDIA RTX 3060 GPU. It also provides five models of unmanned underwater vehicles (UUVs), multiple propulsion systems, and a set of predefined tasks covering core underwater control challenges. Additionally, the DR toolkit allows flexible adjustments of simulation and task parameters during training to improve Sim2Real transfer. Further benchmark experiments demonstrate that MarineGym improves training efficiency over existing platforms and supports robust policy adaptation under various perturbations. We expect this platform could drive further advancements in RL research for underwater robotics. For more details about MarineGym and its applications, please visit our project page: https://marine-gym.com/.