# RL-PGO: Reinforcement Learning-based Planar Pose-Graph Optimization

arXiv: https://arxiv.org/abs/2202.13221 · HTML: https://mlsanity.com/paper/2202.13221/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 26 Feb 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Soft Actor-Critic Algorithms and Applications](https://mlsanity.com/paper/1812.05905/) (2018)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age](https://mlsanity.com/paper/1606.05830/) (2016)
- [Reinforcement Learning in Healthcare: A Survey](https://mlsanity.com/paper/1908.08796/) (2019)
- [An Introduction to Deep Reinforcement Learning](https://mlsanity.com/paper/1811.12560/) (2018)
- [BA-Net: Dense Bundle Adjustment Network](https://mlsanity.com/paper/1806.04807/) (2018)
- [SE-Sync: A Certifiably Correct Algorithm for Synchronization over the Special Euclidean Group](https://mlsanity.com/paper/1612.07386/) (2016)
- [Memory-based control with recurrent neural networks](https://mlsanity.com/paper/1512.04455/) (2015)
- [Shonan Rotation Averaging: Global Optimality by Surfing SO(p)n](https://mlsanity.com/paper/2008.02737/) (2020)
- [NeuRoRA: Neural Robust Rotation Averaging](https://mlsanity.com/paper/1912.04485/) (2019)
- [LS-Net: Learning to Solve Nonlinear Least Squares for Monocular Stereo](https://mlsanity.com/paper/1809.02966/) (2018)
- [FutureMapping 2: Gaussian Belief Propagation for Spatial AI](https://mlsanity.com/paper/1910.14139/) (2019)
- [Distributed Certifiably Correct Pose-Graph Optimization](https://mlsanity.com/paper/1911.03721/) (2019)
- [Differentiable Factor Graph Optimization for Learning Smoothers](https://mlsanity.com/paper/2105.08257/) (2021)
- [Bundle Adjustment on a Graph Processor](https://mlsanity.com/paper/2003.03134/) (2020)
- [Performance Guarantees for Spectral Initialization in Rotation Averaging and Pose-Graph SLAM](https://mlsanity.com/paper/2201.03773/) (2022)
- [Bundle Adjustment Revisited](https://mlsanity.com/paper/1912.03858/) (2019)
- [Guaranteed Globally Optimal Planar Pose Graph and Landmark SLAM via Sparse-Bounded Sums-of-Squares Programming](https://mlsanity.com/paper/1809.07744/) (2018)
- [miniSAM: A Flexible Factor Graph Non-linear Least Squares Optimization Framework](https://mlsanity.com/paper/1909.00903/) (2019)
- [Rotation Averaging with Attention Graph Neural Networks](https://mlsanity.com/paper/2010.06773/) (2020)

## Built on by (most cited first, 4 of 4)

- [Monocular visual simultaneous localization and mapping: (r)evolution from geometry to deep learning-based pipelines](https://mlsanity.com/paper/2503.02955/) (2025)
- [A Survey on Reinforcement Learning Applications in SLAM](https://mlsanity.com/paper/2408.14518/) (2024)
- [Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAM](https://mlsanity.com/paper/2510.22740/) (2025)
- [MARVO: Marine-Adaptive Radiance-aware Visual Odometry](https://mlsanity.com/paper/2511.22860/) (2025)

## Abstract (arXiv)

The objective of pose SLAM or pose-graph optimization (PGO) is to estimate the trajectory of a robot given odometric and loop closing constraints. State-of-the-art iterative approaches typically involve the linearization of a non-convex objective function and then repeatedly solve a set of normal equations. Furthermore, these methods may converge to a local minima yielding sub-optimal results. In this work, we present to the best of our knowledge the first Deep Reinforcement Learning (DRL) based environment and proposed agent for 2D pose-graph optimization. We demonstrate that the pose-graph optimization problem can be modeled as a partially observable Markov Decision Process and evaluate performance on real-world and synthetic datasets. The proposed agent outperforms state-of-the-art solver g2o on challenging instances where traditional nonlinear least-squares techniques may fail or converge to unsatisfactory solutions. Experimental results indicate that iterative-based solvers bootstrapped with the proposed approach allow for significantly higher quality estimations. We believe that reinforcement learning-based PGO is a promising avenue to further accelerate research towards globally optimal algorithms. Thus, our work paves the way to new optimization strategies in the 2D pose SLAM domain.