Advantage Alignment Does Not Preserve Mixed Nash Equilibria: A Machine-Checked Counterexample and an Exact Covariance Characterization

Advantage Alignment (Duque et al., ICLR 2025) states that its alignment term vanishes at every Nash equilibrium. We construct a two-stage game whose unique Markov-perfect equilibrium is completely mixed and at which the update is nonzero; after one step the other player has a strictly profitable deviation. The alignment term equals a pre-action weight times the covariance between the agent's score and the welfare externality of its action on the opponent; the update is not invariant to strategic equivalence; and in normal-form games AA reads only the opponent's welfare externality whereas first-order LOLA reads only the interaction that changes the opponent's incentives. Main statements are machine-checked in Lean 4 with Mathlib. Advantage Alignment, its Equation 8 and Theorem 3 are the work of Duque, Aghajohari, Cooijmans, Ciuca, Zhang, Gidel and Courville.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24325532
Primary Topic
Game Theory and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Advantage Alignment Does Not Preserve Mixed Nash Equilibria: A Machine-Checked Counterexample and an Exact Covariance Characterization

Alejandro Panera Pascual
Zenodo (CERN European Organization for Nuclear Research)
Game Theory and Applications
preprint

Advantage Alignment Does Not Preserve Mixed Nash Equilibria: A Machine-Checked Counterexample and an Exact Covariance Characterization

Alejandro Panera Pascual
preprint en

Abstract

Advantage Alignment (Duque et al., ICLR 2025) states that its alignment term vanishes at every Nash equilibrium. We construct a two-stage game whose unique Markov-perfect equilibrium is completely mixed and at which the update is nonzero; after one step the other player has a strictly profitable deviation. The alignment term equals a pre-action weight times the covariance between the agent's score and the welfare externality of its action on the opponent; the update is not invariant to strategic equivalence; and in normal-form games AA reads only the opponent's welfare externality whereas first-order LOLA reads only the interaction that changes the opponent's incentives. Main statements are machine-checked in Lean 4 with Mathlib. Advantage Alignment, its Equation 8 and Theorem 3 are the work of Duque, Aghajohari, Cooijmans, Ciuca, Zhang, Gidel and Courville.

Zenodo (CERN European Organization for Nuclear Research)
Universidad de Salamanca (ES)
Game Theory and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon