Explanation through Reward Model Reconciliation using POMDP Tree Search
On the map: LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
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.
Key facts. Cited by 1 paper 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.
Builds on
5 of 18 references.
References · 5
- 2016DESPOT: Online POMDP Planning with Regularizationcited by 106
- 2020The Emerging Landscape of Explainable AI Planning and Decision Makingcited by 44
- 2017"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 relationshipscited by 22
- 2019Model-Free Model Reconciliationcited by 8
- 2021Task-Guided Inverse Reinforcement Learning Under Partial Informationcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2023Evaluating the Impact of Personalized Value Alignment in Human-Robot Interaction: Insights into Trust and Team Performance Outcomes
- 2018Scalable agent alignment via reward modeling: a research direction
- 2024AI Alignment with Changing and Influenceable Reward Functions
- 2020DERAIL: Diagnostic Environments for Reward And Imitation Learning
- 2024Value Alignment and Trust in Human-Robot Interaction: Insights from Simulation and User Study
- 2024Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
- 2025Reward Models in Deep Reinforcement Learning: A Survey
- 2025Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization