Learning in games with non rational preferences of agents

Le descriptif de l’offre ci-dessous est en Anglais

Niveau de diplôme exigé : Bac + 3 ou équivalent

Fonction : Stagiaire de la recherche

Contexte et atouts du poste

Within the framework of a partnership:

  • collaboration between 2 Inria teams: ARGO (Paris) and INOCS (Lille),
  • project: Inria - EDF Challenge. 

Is regular travel foreseen for this post ? No.

 

Mission confiée

The aim of this internship is to investigate learning methods to be applied in multi agent games where agents have utilities that are shaped by non rational preferences. Prospect theory is used to model these preferences. The utility functions that arise consequently are non smooth and non convex. The internship will explore the implementation and analysis of  learning algorithms in such games. In particular, the use of minorization-maximization based methods for learning equilibria  will be studied.

Supervision: Ashok Krishnan KS, Ana Busic, Hélène Le Cadre

Main contact: Ashok Krishnan KS, ashok-krishnan.komalan-sindhu@inria.fr

For a better knowledge of the proposed research subject:

  1. Ashok Krishnan K. S., Hélène Le Cadre, Ana Bušić. How Irrationality Shapes Nash Equilibria: A Prospect-Theoretic Perspective. 64th IEEE Conference on Decision and Control (CDC) 2025, Dec 2025, Rio de Jaineiro, Brazil. https://hal.science/hal-05036781v2 
  2. Ashok Krishnan, Hélène Le Cadre, Ana Bušić. Achieving a Collective Target Through Incentives. NETGCOOP 2025 - 12th International Conference of Networks, Games, Control and Optimization, Oct 2025, Bilbao, Spain. https://hal.science/hal-05424025v1

Principales activités

The candidate will:

  • Review relevant literature
  • Identify minorizing functions for classes of games
  • Implement learning algorithms
  • Analyze and report the results

 

Compétences

Technical skills and level required: optimisation, Python

Languages: English

Other valued appreciated: game theory

Avantages

  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage