# Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice

arXiv: https://arxiv.org/abs/2311.07745 · HTML: https://mlsanity.com/paper/2311.07745/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 17 of 17)

- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Learning Likelihoods with Conditional Normalizing Flows](https://mlsanity.com/paper/1912.00042/) (2019)
- [Deep Variational Reinforcement Learning for POMDPs](https://mlsanity.com/paper/1806.02426/) (2018)
- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [Online algorithms for POMDPs with continuous state, action, and observation spaces](https://mlsanity.com/paper/1709.06196/) (2017)
- [Particle Filter Networks with Application to Visual Localization](https://mlsanity.com/paper/1805.08975/) (2018)
- [Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors](https://mlsanity.com/paper/1805.11122/) (2018)
- [QMDP-Net: Deep Learning for Planning under Partial Observability](https://mlsanity.com/paper/1703.06692/) (2017)
- [DualSMC: Tunneling Differentiable Filtering and Planning under Continuous POMDPs](https://mlsanity.com/paper/1909.13003/) (2019)
- [Optimality Guarantees for Particle Belief Approximation of POMDPs](https://mlsanity.com/paper/2210.05015/) (2022)
- [An On-Line POMDP Solver for Continuous Observation Spaces](https://mlsanity.com/paper/2011.02076/) (2020)
- [Compositional Learning-based Planning for Vision POMDPs](https://mlsanity.com/paper/2112.09456/) (2021)
- [Sparse tree search optimality guarantees in POMDPs with continuous observation spaces](https://mlsanity.com/paper/1910.04332/) (2019)
- [D2A-BSP: Distilled Data Association Belief Space Planning with Performance Guarantees Under Budget Constraints](https://mlsanity.com/paper/2202.04954/) (2022)
- [Multilevel Monte-Carlo for Solving POMDPs Online](https://mlsanity.com/paper/1907.09673/) (2019)
- [Data Association Aware POMDP Planning with Hypothesis Pruning Performance Guarantees](https://mlsanity.com/paper/2303.02139/) (2023)

## Built on by (most cited first, 2 of 2)

- [Towards Optimal Performance and Action Consistency Guarantees in Dec-POMDPs with Inconsistent Beliefs and Limited Communication](https://mlsanity.com/paper/2512.20778/) (2025)
- [REBA: A Revealed Belief Automaton Framework for Online Planning in Continuous POMDPs](https://mlsanity.com/paper/2606.21971/) (2026)

## Abstract (arXiv)

Solving partially observable Markov decision processes (POMDPs) with high dimensional and continuous observations, such as camera images, is required for many real life robotics and planning problems. Recent researches suggested machine learned probabilistic models as observation models, but their use is currently too computationally expensive for online deployment. We deal with the question of what would be the implication of using simplified observation models for planning, while retaining formal guarantees on the quality of the solution. Our main contribution is a novel probabilistic bound based on a statistical total variation distance of the simplified model. We show that it bounds the theoretical POMDP value w.r.t. original model, from the empirical planned value with the simplified model, by generalizing recent results of particle-belief MDP concentration bounds. Our calculations can be separated into offline and online parts, and we arrive at formal guarantees without having to access the costly model at all during planning, which is also a novel result. Finally, we demonstrate in simulation how to integrate the bound into the routine of an existing continuous online POMDP solver.