Non-Holonomic Gradient Play: Leafwise Nash Equilibria, Stability, and Deception
Abstract
We study generalized learning dynamics in multi-agent systems whose joint state evolves on a manifold and whose agents act through state-dependent, potentially nonholonomic vector fields. Under a bundle-splitting condition, we show that these dynamics admit an intrinsic representation as projected Riemannian gradients, giving rise to a class of \emph{nonholonomic gradient play} dynamics. We characterize the local stability of its equilibria through an intrinsic linearization that explicitly captures the effects of the Riemannian connection and the nonholonomy of the actuation frame. The framework recovers classical gradient play on Euclidean spaces and manifolds as special cases while accommodating nonholonomic actuation. We then develop a geometric theory of deception under asymmetric information, whereby an agent exploits privileged knowledge of other agents' learning rules to manipulate the emerging equilibrium. We show that deception effectively \emph{tilts the Riemannian geometry} perceived by the oblivious agents, distorting their projected gradient directions. We establish persistence of exponentially stable equilibria over an open set of deception parameters and derive an explicit first-order characterization of the resulting equilibrium displacement. Analytical and numerical examples illustrate the framework and its implications for equilibrium manipulation in games.
Related
- On the stability of equilibria in degenerate periodic Hamiltonian systems
- Typical number and stability of equilibria in large non-reciprocal complex systems
- Equilibria in Motion: Stability, Tracking, and Convergence
- Regulating All Induced Equilibria: Counterexample-Coupled Incentive–Certificate Synthesis for Financial Stability
- Existence and Stability of Dancing Equilibria in Asymmetric Kuramoto Networks
BibTeX
@misc{abdelgalil2026nonholonomic,
title = {{Non-Holonomic Gradient Play: Leafwise Nash Equilibria, Stability, and Deception}},
author = {Mahmoud Abdelgalil and Miroslav Krstic and Jorge I. Poveda},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.38051},
eprint = {2609.38051},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.38051},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Non-Holonomic Gradient Play: Leafwise Nash Equilibria, Stability, and Deception
AU - Mahmoud Abdelgalil
AU - Miroslav Krstic
AU - Jorge I. Poveda
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2609.38051
UR - https://arxiv.org/abs/2609.38051
AB - We study generalized learning dynamics in multi-agent systems whose joint state evolves on a manifold and whose agents act through state-dependent, potentially nonholonomic vector fields. Under a bundle-splitting condition, we show that these dynamics admit an intrinsic representation as projected Riemannian gradients, giving rise to a class of \emph{nonholonomic gradient play} dynamics. We characterize the local stability of its equilibria through an intrinsic linearization that explicitly captures the effects of the Riemannian connection and the nonholonomy of the actuation frame. The framework recovers classical gradient play on Euclidean spaces and manifolds as special cases while accommodating nonholonomic actuation. We then develop a geometric theory of deception under asymmetric information, whereby an agent exploits privileged knowledge of other agents' learning rules to manipulate the emerging equilibrium. We show that deception effectively \emph{tilts the Riemannian geometry} perceived by the oblivious agents, distorting their projected gradient directions. We establish persistence of exponentially stable equilibria over an open set of deception parameters and derive an explicit first-order characterization of the resulting equilibrium displacement. Analytical and numerical examples illustrate the framework and its implications for equilibrium manipulation in games.
ER -