Verified Causal Reinforcement Learning for Robust Transfer under Distribution Shift

When:
20/12/2026 – 21/12/2026 all-day
2026-12-20T01:00:00+01:00
2026-12-21T01:00:00+01:00

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : LITIS, Université de Rouen Normandie, INSA Rouen N
Durée : 3 years
Contact : aleite@insa-rouen.fr
Date limite de publication : 2026-12-20

Contexte :
We are recruiting a PhD candidate at LITIS, Université de Rouen Normandie / INSA Rouen Normandie (France) for a 3-year doctoral project on Verified Causal Reinforcement Learning for Robust Transfer under Distribution Shift.

Sujet :
The project lies at the intersection of causal inference, reinforcement learning, transfer/generalization, and formal verification with Lean. It will investigate how invariant causal mechanisms can support robust policy transfer across changing environments and how selected semantic, transfer, and safety properties can be machine-checked.

See attached file for the full description.

Profil du candidat :
Candidates should hold, or be about to obtain, an M2/Master’s degree or engineering diploma in Applied Mathematics, Computer Science, Data Science, or a related field. Prior experience in RL, causal inference, or Lean is appreciated but not required.

Formation et compétences requises :

Adresse d’emploi :
Rouen Normandie

Document attaché : 202609141134_litis_thesis_proposal_verified_causal_rl.pdf