SOURCE-LINKED INTELLIGENCE

GzDRL: Reproducible and Scalable Deep Reinforcement Learning with Gazebo

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global