# Policy Aggregation

Source: [Policy Aggregation](<https://www.sota2.com/research/paper/68fa759f1e209131cea69044>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-02T07:57:36.168Z

Authors: Parand A. Alamdari, Soroush Ebadian, Ariel D. Procaccia

Published: 2024-11-06T04:19:50.000Z

## Abstract

We consider the challenge of AI value alignment with multiple individuals that have different reward functions and optimal policies in an underlying Markov decision process. We formalize this problem as one of policy aggregation, where the goal is to identify a desirable collective policy. We argue that an approach informed by social choice theory is especially suitable. Our key insight is that social choice methods can be reinterpreted by identifying ordinal preferences with volumes of subsets of the state-action occupancy polytope. Building on this insight, we demonstrate that a variety of methods--including approval voting, Borda count, the proportional veto core, and quantile fairness--can be practically applied to policy aggregation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Policy Optimization on 5 symmetric agents, one per warehouse (test)](<https://www.sota2.com/research/sota/policy-optimization-on-5-symmetric-agents-one-per-warehouse-test.md>): Policy Optimization; 5 symmetric agents, one per warehouse (test); Gini Index: 0.0188.

- [Policy Optimization on 10 agents, random subsets of warehouses (test)](<https://www.sota2.com/research/sota/policy-optimization-on-10-agents-random-subsets-of-warehouses-test.md>): Policy Optimization; 10 agents, random subsets of warehouses (test); Gini Index: 0.0625.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.03651>)

[PDF](<https://arxiv.org/pdf/2411.03651.pdf>)

[Implementation](<https://github.com/praal/policy-aggregation.>)
