# Explanation through Reward Model Reconciliation using POMDP Tree Search

arXiv: https://arxiv.org/abs/2305.00931 · HTML: https://mlsanity.com/paper/2305.00931/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reward modeling and RLHF, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 5 of its 18 references that are in the map.
- First posted on arXiv 1 May 2023.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Reward modeling and RLHF](https://mlsanity.com/alignment/reward-modeling-and-rlhf/)

## Builds on (most cited first, 5 of 5)

- [DESPOT: Online POMDP Planning with Regularization](https://mlsanity.com/paper/1609.03250/) (2016)
- [The Emerging Landscape of Explainable AI Planning and Decision Making](https://mlsanity.com/paper/2002.11697/) (2020)
- ["Dave...I can assure you...that it's going to be all right..." -- A definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships](https://mlsanity.com/paper/1711.03846/) (2017)
- [Model-Free Model Reconciliation](https://mlsanity.com/paper/1903.07198/) (2019)
- [Task-Guided Inverse Reinforcement Learning Under Partial Information](https://mlsanity.com/paper/2105.14073/) (2021)

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

- [Robustness Analysis of POMDP Policies to Observation Perturbations](https://mlsanity.com/paper/2604.21256/) (2026)

## Abstract (arXiv)

As artificial intelligence (AI) algorithms are increasingly used in mission-critical applications, promoting user-trust of these systems will be essential to their success. Ensuring users understand the models over which algorithms reason promotes user trust. This work seeks to reconcile differences between the reward model that an algorithm uses for online partially observable Markov decision (POMDP) planning and the implicit reward model assumed by a human user. Action discrepancies, differences in decisions made by an algorithm and user, are leveraged to estimate a user's objectives as expressed in weightings of a reward function.