# GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo

arXiv: https://arxiv.org/abs/2609.13243 · HTML: https://mlsanity.com/paper/2609.13243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 3 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 16 of 16)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles](https://mlsanity.com/paper/1705.05065/) (2017)
- [Robot Operating System 2: Design, Architecture, and Uses In The Wild](https://mlsanity.com/paper/2211.07752/) (2022)
- [Flightmare: A Flexible Quadrotor Simulator](https://mlsanity.com/paper/2009.00563/) (2020)
- [Learning to Fly -- a Gym Environment with PyBullet Physics for Reinforcement Learning of Multi-agent Quadcopter Control](https://mlsanity.com/paper/2103.02142/) (2021)
- [EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine](https://mlsanity.com/paper/2206.10558/) (2022)
- [Real-Time Reinforcement Learning](https://mlsanity.com/paper/1911.04448/) (2019)
- [Autonomous Drone Racing: A Survey](https://mlsanity.com/paper/2301.01755/) (2023)
- [OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control](https://mlsanity.com/paper/2309.12825/) (2023)
- [Learning to Fly in Seconds](https://mlsanity.com/paper/2311.13081/) (2023)
- [Gym-Ignition: Reproducible Robotic Simulations for Reinforcement Learning](https://mlsanity.com/paper/1911.01715/) (2019)
- [Aerial Gym -- Isaac Gym Simulator for Aerial Robots](https://mlsanity.com/paper/2305.16510/) (2023)
- [robo-gym -- An Open Source Toolkit for Distributed Deep Reinforcement Learning on Real and Simulated Robots](https://mlsanity.com/paper/2007.02753/) (2020)
- [Handling Delay in Real-Time Reinforcement Learning](https://mlsanity.com/paper/2503.23478/) (2025)
- [PIC4rl-gym: a ROS2 modular framework for Robots Autonomous Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2211.10714/) (2022)

## Abstract (arXiv)

We present GzDRL, a novel single-process reinforcement learning (RL) framework for Gazebo that overcomes longstanding bottlenecks in scalable, reproducible robotics experimentation. Unlike conventional middleware-based RL-Gazebo integrations that suffer from nondeterminism and irreproducibility, GzDRL introduces a systematic, middleware-free environment-stepping mechanism that directly synchronizes agent actions and physics updates. This design enables deterministic, high-throughput data collection, efficient vectorization, and reproducible RL training and evaluation. Comprehensive benchmarks demonstrate that GzDRL achieves the highest workstation throughput among the evaluated frameworks while remaining competitive with GPU-accelerated simulators on laptop hardware, and maintains precise agent-environment synchronization, multi-agent scalability, and experiment-level reproducibility. We further validate sim-to-real transfer by deploying learned policies directly onto a physical quadrotor, without fine-tuning. Our results establish GzDRL as an accessible and reproducible platform for advancing RL in robotics and automation.