Inferring Lexicographically-Ordered Rewards from Preferences
Not on the map. Why?
Abstract (arXiv)
Modeling the preferences of agents over a set of alternatives is a principal concern in many areas. The dominant approach has been to find a single reward/utility function with the property that alternatives yielding higher rewards are preferred over alternatives yielding lower rewards. However, in many settings, preferences are based on multiple, often competing, objectives; a single reward function is not adequate to represent such preferences. This paper proposes a method for inferring multi-objective reward-based representations of an agent's observed preferences. We model the agent's priorities over different objectives as entering lexicographically, so that objectives with lower priorities matter only when the agent is indifferent with respect to objectives with higher priorities. We offer two example applications in healthcare, one inspired by cancer treatment, the other inspired by organ transplantation, to illustrate how the lexicographically-ordered rewards we learn can provide a better understanding of a decision-maker's preferences and help improve policies when used in reinforcement learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 6 of its 54 references that are in the map. First posted on arXiv 21 Feb 2022.
Builds on
6 of 54 references.
References · 6
- 2017Deep reinforcement learning from human preferencescited by 3,846
- 2016Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimizationcited by 400
- 2018Reward learning from human preferences and demonstrations in Ataricited by 314
- 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 256
- 2019Maximum Likelihood Constraint Inference for Inverse Reinforcement Learningcited by 33
- 2018Learning Constraints from Demonstrationscited by 9
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.