Publications

• 2023 M. Iseri, & J. Zhang, Set Valued Hamilton-Jacobi-Bellman Equations, The Annals of Probability (accepted, 2026).  Slides   BoardTalk 
   abstract 

  Building upon the dynamic programming principle for set-valued functions arising from many applications, in this paper we propose a new notion of set-valued PDEs. The key component in the theory is a set-valued It\^{o} formula, characterizing the flows on the surface of the dynamic sets. In the contexts of multivariate control problems, we establish the wellposedness of the set-valued HJB equations, which extends the standard HJB equations in the scalar case to the multivariate case. As an application, a moving scalarization for certain time inconsistent problems is constructed by using the classical solution of the set-valued HJB equation.
• 2021 M. Iseri, & J. Zhang, Set Values for Mean Field Games, Transactions of the American Mathematical Society (2024).  Slides   WebTalk 
   abstract 

  When a mean field game satisfies certain monotonicity conditions, the mean field equilibrium is unique and the corresponding value function satisfies the so called master equation. In general, however, there can be multiple equilibriums which typically lead to different values. In this paper we study the set of values over all mean field equilibriums, which we call the set value of the game. We shall establish two main properties of the set value: (i) the dynamic programming principle; (ii) the convergence of the set values of the corresponding N-player games. We emphasize that the set value is very sensitive to the choice of the admissible controls. For the dynamic programming principle, one needs to use closed loop controls (instead of open loop controls). For the convergence, one has to restrict to the same type of equilibriums for the N-player game and for the mean field game. We shall investigate three cases, two in finite state space models and the other in a diffusion model.
• 2016 M. Iseri, D. Kaspar, & M. Mungan, Depinning as a coagulation process, EPL (Europhysics Letters)
  (paper was selected Editor's Choice, appeared on Highlights 2016).
   abstract 

  We consider a one-dimensional model that describes the depinning of an elastic string of particles in a strongly pinning, phase-disordered periodic environment under a slowly increasing force. The evolution towards depinning occurs by the triggering of avalanches in regions of activity which are at first isolated, but later grow and merge. For large system sizes the dynamically critical behavior is dominated by the coagulation of these active regions. Our analysis and numerical simulations show that the evolution of the sizes of active regions is well described by a Smoluchowski coagulation equation, allowing us to predict correlation lengths and avalanche sizes in terms of certain moments of the size distribution.

Preprints

• 2025 M. Iseri, & E. Bayraktar, The Learning Approach to Games, arXiv:2503.00227. Submitted.  Slides 
   abstract 

  This work introduces a unified framework for analyzing games in greater depth. In the existing literature, players’ strategies are typically assigned scalar values, and equilibrium concepts are used to identify compatible choices. However, this approach neglects the internal structure of players, thereby failing to accurately model observed behaviors.
  
  To address this limitation, we propose an abstract definition of a player, consistent with constructions in reinforcement learning. Instead of defining games as external settings, our framework defines them in terms of the players themselves. This offers a language that enables a deeper connection between games and learning. To illustrate the need for this generality, we study a simple two-player game and show that even in basic settings, a sophisticated player may adopt dynamic strategies that cannot be captured by simpler models or compatibility analysis.
  
  For a general definition of a player, we discuss natural conditions on its components and define competition through their behavior. In the discrete setting, we consider players whose estimates largely follow the standard framework from the literature. We explore connections to correlated equilibrium and highlight that dynamic programming naturally applies to all estimates. In the mean-field setting, we exploit symmetry to construct explicit examples of equilibria. Finally, we conclude by examining relations to reinforcement learning.