mlsanityData to 14 Oct 2026

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

arXiv 2503.09203 ↗First posted 12 Mar 2025cs.RO cs.LGcited by 8

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

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/.

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.

Builds on

14 of 51 references.

References · 14

  1. 2016OpenAI Gymcited by 1,736
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  4. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  5. 2019Active Domain Randomizationcited by 170
  6. 2024HOVER: Versatile Neural Whole-Body Controller for Humanoid Robotscited by 91
  7. 2023OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Controlcited by 33
  8. 2023UNav-Sim: A Visually Realistic Underwater Robotics Simulator and Synthetic Data-generation Frameworkcited by 17
  9. 2022DAVE Aquatic Virtual Environment: Toward a General Underwater Robotics Simulatorcited by 11
  10. 2025Stonefish: Supporting Machine Learning Research in Marine Roboticscited by 11
  11. 2021Deep Reinforcement Learning for Continuous Docking Control of Autonomous Underwater Vehicles: A Benchmarking Studycited by 6
  12. 2019Multi Pseudo Q-learning Based Deterministic Policy Gradient for Tracking Control of Autonomous Underwater Vehiclescited by 4
2 more
  1. 2017Online Approximate Optimal Station Keeping of a Marine Craft in the Presence of a Currentcited by 3
  2. 2024AAM-SEALS: Developing Aerial-Aquatic Manipulators in SEa, Air, and Land Simulatorcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AIcited by 16
  2. 2025Fast Policy Learning for 6-DOF Position Control of Underwater Vehiclescited by 3
  3. 2025OceanGym: A Benchmark Environment for Underwater Embodied Agentscited by 1
  4. 2026Average-Power-Budgeted Underwater Vehicle Control via Constrained Reinforcement Learningcited by 0
  5. 2026Towards Scaling Marine Perception with Synthetic Datacited by 0
  6. 2026AquaOrbit: Sim-to-Real Reinforcement Learning for Underwater Target Orbiting under Intermittent Visual Feedbackcited by 0
  7. 2026A Unified Dynamics Framework for Reinforcement Learning and Classical Control of a Six-DOF Pipeline-Tracking ROV in NVIDIA Isaac Simcited by 0
  8. 2026Sim-to-Real RL for ASVs using SysIDcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MarineGym: Accelerated Training for Underwater Vehicles with High-Fidelity RL Simulation
  2. 2024Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning
  3. 2024Learning Agile Swimming: An End-to-End Approach without CPGs
  4. 2025Scaling Multi Agent Reinforcement Learning for Underwater Acoustic Tracking via Autonomous Vehicles
  5. 2025The HydroGym Reinforcement Learning Platform for Fluid Dynamics
  6. 2025Ocean Diviner: A Diffusion-Augmented Reinforcement Learning Framework for AUV Robust Control in Underwater Tasks
  7. 2026CORL-AUV: CFD Oriented Reinforcement Learning for Autonomous Underwater Vehicles
  8. 2025EasyUUV: An LLM-Enhanced Universal and Lightweight Sim-to-Real Reinforcement Learning Framework for UUV Attitude Control ↗