# Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent

arXiv: https://arxiv.org/abs/2403.17358 · HTML: https://mlsanity.com/paper/2403.17358/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 14 references that are in the map.
- First posted on arXiv 26 Mar 2024.

## Builds on (most cited first, 4 of 4)

- [A Survey of Multi-Objective Sequential Decision-Making](https://mlsanity.com/paper/1402.0590/) (2014)
- [Partially Observable Markov Decision Processes (POMDPs) and Robotics](https://mlsanity.com/paper/2107.07599/) (2021)
- [A POMDP Model for Safe Geological Carbon Sequestration](https://mlsanity.com/paper/2212.00669/) (2022)
- [Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascent](https://mlsanity.com/paper/2212.12154/) (2022)

## Built on by (most cited first, 1 of 1)

- [REBA: A Revealed Belief Automaton Framework for Online Planning in Continuous POMDPs](https://mlsanity.com/paper/2606.21971/) (2026)

## Abstract (arXiv)

Lagrangian-guided Monte Carlo tree search with global dual ascent has been applied to solve large constrained partially observable Markov decision processes (CPOMDPs) online. In this work, we demonstrate that these global dual parameters can lead to myopic action selection during exploration, ultimately leading to suboptimal decision making. To address this, we introduce history-dependent dual variables that guide local action selection and are optimized with recursive dual ascent. We empirically compare the performance of our approach on a motivating toy example and two large CPOMDPs, demonstrating improved exploration, and ultimately, safer outcomes.