---
OA_place: publisher
OA_type: hybrid
_id: '19965'
abstract:
- lang: eng
text: Multiagent learning is challenging when agents face mixed-motivation interactions,
where conflicts of interest arise as agents independently try to optimize their
respective outcomes. Recent advancements in evolutionary game theory have identified
a class of “zero-determinant” strategies, which confer an agent with significant
unilateral control over outcomes in repeated games. Building on these insights,
we present a comprehensive generalization of zero-determinant strategies to stochastic
games, encompassing dynamic environments. We propose an algorithm that allows
an agent to discover strategies enforcing predetermined linear (or approximately
linear) payoff relationships. Of particular interest is the relationship in which
both payoffs are equal, which serves as a proxy for fairness in symmetric games.
We demonstrate that an agent can discover strategies enforcing such relationships
through experience alone, without coordinating with an opponent. In finding and
using such a strategy, an agent (“enforcer”) can incentivize optimal and equitable
outcomes, circumventing potential exploitation. In particular, from the opponent’s
viewpoint, the enforcer transforms a mixed-motivation problem into a cooperative
problem, paving the way for more collaboration and fairness in multiagent systems.
acknowledgement: 'We gratefully acknowledge the support from the European Research
Council (Starting Grant 850529: E-DIRECT) and the Max Planck Society (C.H.), the
European Research Council (Consolidator Grant 863818: ForM-SMArt) (K.C.), the Shanghai
Pujiang Program (No. 23PJ1405500) (Q.S.), the Army Research Office (Grant No. W911NF-18-1-0325)
(N.E.L.), and the John Templeton Foundation (Grant No. 62281) (J.B.P.).'
article_number: e2319927121
article_processing_charge: Yes (in subscription journal)
article_type: original
author:
- first_name: Alex
full_name: Mcavoy, Alex
last_name: Mcavoy
- first_name: Udari Madhushani
full_name: Sehwag, Udari Madhushani
last_name: Sehwag
- first_name: Christian
full_name: Hilbe, Christian
id: 2FDF8F3C-F248-11E8-B48F-1D18A9856A87
last_name: Hilbe
orcid: 0000-0001-5116-955X
- first_name: Krishnendu
full_name: Chatterjee, Krishnendu
id: 2E5DCA20-F248-11E8-B48F-1D18A9856A87
last_name: Chatterjee
orcid: 0000-0002-4561-241X
- first_name: Wolfram
full_name: Barfuss, Wolfram
last_name: Barfuss
- first_name: Qi
full_name: Su, Qi
last_name: Su
- first_name: Naomi Ehrich
full_name: Leonard, Naomi Ehrich
last_name: Leonard
- first_name: Joshua B.
full_name: Plotkin, Joshua B.
last_name: Plotkin
citation:
ama: Mcavoy A, Sehwag UM, Hilbe C, et al. Unilateral incentive alignment in two-agent
stochastic games. Proceedings of the National Academy of Sciences. 2025;122(25).
doi:10.1073/pnas.2319927121
apa: Mcavoy, A., Sehwag, U. M., Hilbe, C., Chatterjee, K., Barfuss, W., Su, Q.,
… Plotkin, J. B. (2025). Unilateral incentive alignment in two-agent stochastic
games. Proceedings of the National Academy of Sciences. National Academy
of Sciences. https://doi.org/10.1073/pnas.2319927121
chicago: Mcavoy, Alex, Udari Madhushani Sehwag, Christian Hilbe, Krishnendu Chatterjee,
Wolfram Barfuss, Qi Su, Naomi Ehrich Leonard, and Joshua B. Plotkin. “Unilateral
Incentive Alignment in Two-Agent Stochastic Games.” Proceedings of the National
Academy of Sciences. National Academy of Sciences, 2025. https://doi.org/10.1073/pnas.2319927121.
ieee: A. Mcavoy et al., “Unilateral incentive alignment in two-agent stochastic
games,” Proceedings of the National Academy of Sciences, vol. 122, no.
25. National Academy of Sciences, 2025.
ista: Mcavoy A, Sehwag UM, Hilbe C, Chatterjee K, Barfuss W, Su Q, Leonard NE, Plotkin
JB. 2025. Unilateral incentive alignment in two-agent stochastic games. Proceedings
of the National Academy of Sciences. 122(25), e2319927121.
mla: Mcavoy, Alex, et al. “Unilateral Incentive Alignment in Two-Agent Stochastic
Games.” Proceedings of the National Academy of Sciences, vol. 122, no.
25, e2319927121, National Academy of Sciences, 2025, doi:10.1073/pnas.2319927121.
short: A. Mcavoy, U.M. Sehwag, C. Hilbe, K. Chatterjee, W. Barfuss, Q. Su, N.E.
Leonard, J.B. Plotkin, Proceedings of the National Academy of Sciences 122 (2025).
date_created: 2025-07-06T22:01:23Z
date_published: 2025-06-24T00:00:00Z
date_updated: 2025-09-30T13:47:14Z
day: '24'
ddc:
- '000'
department:
- _id: KrCh
doi: 10.1073/pnas.2319927121
ec_funded: 1
external_id:
isi:
- '001522351900001'
pmid:
- '40523172'
file:
- access_level: open_access
checksum: 3b35befd959a3e37aa9080a64a6afaf3
content_type: application/pdf
creator: dernst
date_created: 2025-07-08T05:52:26Z
date_updated: 2025-07-08T05:52:26Z
file_id: '19972'
file_name: 2025_PNAS_McAvoy.pdf
file_size: 29525932
relation: main_file
success: 1
file_date_updated: 2025-07-08T05:52:26Z
fulldoi: https://doi.org/10.1073/pnas.2319927121
has_accepted_license: '1'
intvolume: ' 122'
isi: 1
issue: '25'
language:
- iso: eng
month: '06'
oa: 1
oa_version: Published Version
pmid: 1
project:
- _id: 0599E47C-7A3F-11EA-A408-12923DDC885E
call_identifier: H2020
grant_number: '863818'
name: 'Formal Methods for Stochastic Models: Algorithms and Applications'
publication: Proceedings of the National Academy of Sciences
publication_identifier:
eissn:
- 1091-6490
issn:
- 0027-8424
publication_status: published
publisher: National Academy of Sciences
quality_controlled: '1'
scopus_import: '1'
status: public
title: Unilateral incentive alignment in two-agent stochastic games
tmp:
image: /images/cc_by_nc_nd.png
legal_code_url: https://creativecommons.org/licenses/by-nc-nd/4.0/legalcode
name: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
(CC BY-NC-ND 4.0)
short: CC BY-NC-ND (4.0)
type: journal_article
user_id: 317138e5-6ab7-11ef-aa6d-ffef3953e345
volume: 122
year: '2025'
...